© 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. 33-TRANSCODER-HP
    4. 54024
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,,,,,,,,
    -0.49
    ,,,,
    -0.44
    ...,
    -0.42
    ”
    -0.40
    ...\
    -0.39
    ,,
    -0.37
    ...)↵
    -0.37
    ķ
    -0.36
    ...↵
    -0.36
    and
    -0.35
    POSITIVE LOGITS
    /&
    0.27
    /^
    0.26
    Enough
    0.26
    =
    0.25
    -
    0.25
    aux
    0.23
    anse
    0.23
    ${
    0.23
    ieces
    0.23
    è´£ç¼ĸ
    0.23
    Activations Density 0.277%

    No Known Activations