© 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. 22-TRANSCODER-HP
    7. 97354
    Prev
    Next
    INDEX
    Explanations

    Code, dates, database queries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tra
    -0.27
    éĹ®æĪij
    -0.27
     FA
    -0.27
    åıį
    -0.27
    Tra
    -0.24
    dr
    -0.24
     Eis
    -0.23
    watch
    -0.23
    å¾®ç¬ij
    -0.23
     ê
    -0.23
    POSITIVE LOGITS
    ilst
    0.31
    abei
    0.30
    andest
    0.27
    mom
    0.27
     dad
    0.27
    arms
    0.25
    omedical
    0.25
    ãģŁãģ¡
    0.25
    èī²ç´ł
    0.25
    geben
    0.24
    Activations Density 0.009%

    No Known Activations