© 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. 107070
    Prev
    Next
    INDEX
    Explanations

    The

    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
    elo
    -0.29
    樯
    -0.27
    udit
    -0.26
    èĩ¨
    -0.25
    azo
    -0.25
    ç·Ĭ
    -0.25
    åŃĹåı·
    -0.25
    erver
    -0.25
    -central
    -0.24
    èIJ½
    -0.24
    POSITIVE LOGITS
     Pall
    0.27
    åı¯æĢľ
    0.26
    resents
    0.26
    첩
    0.26
    AccessException
    0.26
    ä»Ĭ天çļĦ
    0.23
     Opr
    0.23
    sets
    0.23
    $max
    0.23
    éģĵ路交éĢļ
    0.23
    Activations Density 0.910%

    No Known Activations