© 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. 38866
    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
    åŃ©åŃIJçļĦ
    -0.29
    åŃ©åŃIJ们
    -0.28
    _PRIORITY
    -0.27
    é¤ĺ
    -0.24
    WAIT
    -0.24
    é¦
    -0.24
    ÑħваÑĤ
    -0.23
    åŃ©åŃIJ
    -0.23
    reas
    -0.23
    Card
    -0.23
    POSITIVE LOGITS
     teg
    0.29
    ä¸İä¼Ĺ
    0.28
    fte
    0.28
    zte
    0.27
    tem
    0.26
    tribution
    0.25
    ä¸İä¼Ĺä¸įåIJĮ
    0.25
    edException
    0.25
    ial
    0.24
     /^
    0.24
    Activations Density 6.993%

    No Known Activations

    This feature has no known activations.