© 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. 38932
    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
     Voc
    -0.26
    ä¸įå¼Ģ
    -0.25
    TAIL
    -0.25
    IALIZ
    -0.25
    åĩºåı£
    -0.24
    ãĤ¬ãĥ¼
    -0.24
     yaptıģı
    -0.24
     VO
    -0.24
    çĥŃ线
    -0.24
    ialized
    -0.23
    POSITIVE LOGITS
    è¡Į
    0.32
    çīĽ
    0.28
     subdiv
    0.28
    éļľ
    0.28
    ç¼ĸ
    0.26
     ire
    0.25
    iver
    0.25
     ext
    0.25
    åıijå¸ĥæŶéĹ´
    0.24
    妹åŃIJ
    0.24
    Activations Density 0.014%

    No Known Activations

    This feature has no known activations.