© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-4B
    3. 35-TRANSCODER-HP
    4. 39692
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash

    syntax elements and formatting characters in code and technical documentation, such as punctuation, symbols, file extensions, license information, and programming language constructs.

    oai_token-act-pair · deepseek-v3Triggered by @finnwit
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     in
    -0.57
     as
    -0.55
     for
    -0.52
     to
    -0.49
     with
    -0.49
     if
    -0.48
     or
    -0.47
     at
    -0.47
     that
    -0.46
     of
    -0.46
    POSITIVE LOGITS
    -The
    0.44
    .*/↵
    0.41
    \",↵
    0.40
    “The
    0.40
    “(
    0.39
    ',...↵
    0.39
    (The
    0.39
    .But
    0.37
    nThe
    0.37
     “â̦
    0.36
    Activations Density 65.001%

    No Known Activations