© 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. 38817
    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
    Negative Logits
    ä¸įéĶĻ
    -0.27
    è¿ĺä¸įå¦Ĥ
    -0.27
     “
    -0.26
    -grid
    -0.25
    -point
    -0.25
    qd
    -0.25
    ardi
    -0.24
    “
    -0.23
    adj
    -0.23
    ob
    -0.23
    POSITIVE LOGITS
     TSRMLS
    0.28
    讨
    0.26
     domest
    0.26
    /community
    0.24
     notices
    0.24
     noticed
    0.23
    ModuleName
    0.23
    woke
    0.23
     NodeType
    0.23
    å¾Ģ
    0.23
    Activations Density 3.233%

    No Known Activations

    This feature has no known activations.