© 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. 38952
    Prev
    Next
    INDEX
    Explanations

    c

    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
     body
    -0.34
    Body
    -0.29
     Body
    -0.28
    bite
    -0.28
    body
    -0.27
    cha
    -0.27
     len
    -0.25
     colony
    -0.25
     colon
    -0.25
     BODY
    -0.25
    POSITIVE LOGITS
    odom
    0.28
    rost
    0.27
    roma
    0.26
    åģļ人
    0.25
    nth
    0.25
    nier
    0.24
    enity
    0.24
    roc
    0.24
     roc
    0.23
    ä»Ļå¢ĥ
    0.23
    Activations Density 3.212%

    No Known Activations