© 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. 20-TRANSCODER-HP
    7. 62649
    Prev
    Next
    INDEX
    Explanations

    Copyright

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åİŁå§ĭ
    -0.29
    >tag
    -0.28
    ($__
    -0.27
    _original
    -0.26
    efore
    -0.25
    éĻ£
    -0.24
    amina
    -0.24
    æł¹æį®ä¸įåIJĮ
    -0.24
     csvfile
    -0.24
    __,
    -0.23
    POSITIVE LOGITS
    lew
    0.31
    lesen
    0.28
    olut
    0.27
    度
    0.27
    atrice
    0.26
    -wrap
    0.26
    èĤ©è´Ł
    0.25
    ableView
    0.25
    resher
    0.25
     Sw
    0.24
    Activations Density 2.854%

    No Known Activations