© 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. 129170
    Prev
    Next
    INDEX
    Explanations

    Dates and legal documents

    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
    Negative Logits
    è°´
    -0.22
    irus
    -0.22
    irate
    -0.22
    俱
    -0.22
    BOTTOM
    -0.21
     amassed
    -0.21
    éĽħé»ij
    -0.20
    APH
    -0.20
    éĤ£åĦ¿
    -0.20
     lẫn
    -0.20
    POSITIVE LOGITS
    Impro
    0.23
    åIJĮæľŁ
    0.21
    î
    0.21
    aser
    0.21
    åĬłæĭ¿
    0.21
    елÑı
    0.21
    kı
    0.20
    æĸĩç§ij
    0.20
    好人
    0.20
    )č↵č↵č↵
    0.20
    Activations Density 0.003%

    No Known Activations