© 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
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 39314
    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_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
    ddie
    -0.31
    lename
    -0.28
    zcze
    -0.28
    loid
    -0.28
    swagen
    -0.27
    vara
    -0.26
    avirus
    -0.26
    ionales
    -0.25
    uki
    -0.25
    mma
    -0.25
    POSITIVE LOGITS
    gl
    0.37
     RL
    0.37
    RL
    0.36
    GL
    0.34
    rote
    0.28
    gly
    0.27
    ral
    0.27
    гал
    0.27
    Ral
    0.26
    ran
    0.26
    Activations Density 4.466%

    No Known Activations