© 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. 38796
    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
     stand
    -0.29
    adel
    -0.29
    éĻ¤å¤ĸ
    -0.26
    Ĥæķ°
    -0.26
    ä¾ĽçĶµåħ¬åı¸
    -0.25
    åĮ»ç§ij大åѦ
    -0.24
    returnValue
    -0.24
    à¹ģà¸Ļ
    -0.24
    >(*
    -0.24
    eway
    -0.24
    POSITIVE LOGITS
    æĭīåĬ¨
    0.27
    ìŀIJê°Ģ
    0.25
    è¶ĭ
    0.25
    åIJĦ个æĸ¹éĿ¢
    0.25
    æŁ¥å°ģ
    0.25
     повÑĭÑĪен
    0.24
    åĨ²åĬ¨
    0.24
    æĢ¥åī§
    0.24
    ä¸Ģè¡Į
    0.24
    jing
    0.23
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.