© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 38679
    Prev
    Next
    INDEX
    Explanations

    Code/Math

    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
    Negative Logits
    岸边
    -0.28
     innocence
    -0.28
    _Parameter
    -0.27
    eming
    -0.27
    à¹Ģà¸ķ
    -0.27
     tack
    -0.26
     par
    -0.26
    _PAR
    -0.25
    unto
    -0.25
    pee
    -0.25
    POSITIVE LOGITS
    ros
    0.46
     Ros
    0.35
    rose
    0.34
    ç½Ĺæĸ¯
    0.34
    ropsych
    0.31
    Ros
    0.30
    ro
    0.29
    rics
    0.29
    ropolis
    0.28
     Rope
    0.28
    Activations Density 9.636%

    No Known Activations