© 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. 97199
    Prev
    Next
    INDEX
    Explanations

    Working

    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
    oron
    -0.32
    ä¸įä¸Ĭ
    -0.30
    .createNew
    -0.27
     numbering
    -0.27
    ISON
    -0.26
    fare
    -0.26
    /connect
    -0.25
    åŃij
    -0.25
    æī¾å·¥ä½ľ
    -0.24
    æľĢçĪ±
    -0.24
    POSITIVE LOGITS
     ÑģооÑĤвеÑĤÑģÑĤв
    0.27
     Bay
    0.26
    classList
    0.26
    ihn
    0.26
    ä¿Ŀ
    0.25
    /apimachinery
    0.25
    ollar
    0.24
    bove
    0.24
     CO
    0.24
     Washington
    0.23
    Activations Density 0.059%

    No Known Activations