© 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. 40192
    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
    doch
    -0.28
    -ton
    -0.28
     dough
    -0.28
    ixon
    -0.27
    wort
    -0.27
    ushman
    -0.27
    ulary
    -0.27
    inton
    -0.26
    -door
    -0.24
     charity
    -0.24
    POSITIVE LOGITS
    t
    0.31
    éĽĨä¸Ń
    0.28
    éĻĨç»Ń
    0.27
    ä¹ĭ
    0.26
    ï¼Ľ
    0.25
    岸边
    0.25
    0
    0.25
    åıĸ
    0.25
    f
    0.24
    K
    0.24
    Activations Density 19.855%

    No Known Activations

    This feature has no known activations.