© 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. 25-TRANSCODER-HP
    7. 107165
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åħļåĴĮ
    -0.28
    æķĻèĤ²æķĻåѦ
    -0.27
    EMS
    -0.27
    åħ¬å®īæľºåħ³
    -0.27
    ä¸Ģç«Ļ
    -0.27
     interior
    -0.26
    programming
    -0.25
    #else
    -0.25
    WI
    -0.24
    ä¸įåIJĮç±»åŀĭ
    -0.24
    POSITIVE LOGITS
    ierten
    0.29
    utsche
    0.27
     Conf
    0.25
    AndServe
    0.25
    fic
    0.25
    $log
    0.25
    ','.
    0.25
     chips
    0.25
     pe
    0.24
    (Fl
    0.24
    Activations Density 0.401%

    No Known Activations

    This feature has no known activations.