© 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. 30-TRANSCODER-HP
    7. 96992
    Prev
    Next
    INDEX
    Explanations

    mix

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     composed
    -0.45
    ç»ĦæĪIJ
    -0.36
     composing
    -0.36
     composition
    -0.33
     deemed
    -0.31
     compos
    -0.31
    composed
    -0.30
     made
    -0.29
     compositions
    -0.29
     consisting
    -0.28
    POSITIVE LOGITS
    åħ¨éĿ¢
    0.29
    å¾®éĩı
    0.29
     Francesco
    0.29
    èĸĦ
    0.28
     recurse
    0.28
    éĢļ
    0.27
    thickness
    0.27
    quire
    0.27
    -around
    0.26
    æħ·æħ¨
    0.26
    Activations Density 0.107%

    No Known Activations