© 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. 94886
    Prev
    Next
    INDEX
    Explanations

    alon

    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
    aras
    -0.26
    HP
    -0.25
     Perr
    -0.24
     tung
    -0.24
     no
    -0.24
     duct
    -0.23
     lo
    -0.23
     collections
    -0.23
     DP
    -0.23
     lands
    -0.23
    POSITIVE LOGITS
    æĢİä¹Ī说
    0.27
    ä¸Ńå¿ĥ
    0.26
    ioni
    0.26
    bserv
    0.24
    BindingUtil
    0.24
    .Ribbon
    0.24
    æ·±å±Ĥ次
    0.24
     serialVersionUID
    0.24
    夺åĨł
    0.24
    ninger
    0.23
    Activations Density 0.103%

    No Known Activations