© 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. 39803
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ansom
    -0.29
    IRM
    -0.25
    arry
    -0.25
    åĽłä¸ºä»ĸ们
    -0.25
    à¸Ńà¸ĩ
    -0.24
     XB
    -0.24
    ä¸Ģ大
    -0.24
     Provid
    -0.24
    龸çİĭ
    -0.23
    èĥĮä¸Ĭ
    -0.23
    POSITIVE LOGITS
    ãĥ¯ãĤ¤
    0.28
    iful
    0.26
    ews
    0.25
    _literals
    0.24
    th
    0.23
    stein
    0.23
     setC
    0.23
     morph
    0.23
     fal
    0.23
    lings
    0.23
    Activations Density 65.796%

    No Known Activations

    This feature has no known activations.