© 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. 38641
    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
     report
    -0.30
    ä¸įå¦Ĥ
    -0.29
    شت
    -0.29
     reports
    -0.28
    æ¡¡
    -0.27
     Report
    -0.24
    åIJįåŃĹ
    -0.24
     ÑģÑĤÑĥденÑĤ
    -0.24
     pad
    -0.24
    çİĭåŃIJ
    -0.24
    POSITIVE LOGITS
    ariat
    0.28
    ç»ĵæŀĦè°ĥæķ´
    0.26
     [|
    0.26
    subcategory
    0.26
    olvency
    0.25
     Explorer
    0.25
    *M
    0.25
    åıĪ好åıĪå¿«
    0.24
    辫
    0.24
    æľĢ大éĻIJ度
    0.24
    Activations Density 6.997%

    No Known Activations

    This feature has no known activations.