© 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. 109401
    Prev
    Next
    INDEX
    Explanations

    next

    np_max-act-logits · gemini-2.0-flash
    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
    -solid
    -0.29
    å¨ĥ
    -0.29
    èĨĬ
    -0.28
    ç¹ģå¿Ļ
    -0.27
    æĸ¯åŁº
    -0.26
    venient
    -0.26
    头éĥ¨
    -0.25
    groundColor
    -0.25
    é«¡
    -0.25
     resulting
    -0.24
    POSITIVE LOGITS
    è´µ
    0.30
    ä¸ĭåİ»
    0.28
    rove
    0.25
    rema
    0.25
     Asked
    0.25
    /angular
    0.25
     Bip
    0.25
    _Rem
    0.25
    stud
    0.25
     Archive
    0.24
    Activations Density 0.963%

    No Known Activations