© 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. 12-TRANSCODER-HP
    7. 21932
    Prev
    Next
    INDEX
    Explanations

    startups and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çĹĽçĤ¹
    -0.29
    纸
    -0.29
    iture
    -0.27
    iram
    -0.25
    cı
    -0.24
    طرØŃ
    -0.24
    Seeder
    -0.24
    naire
    -0.23
    è¿Ļå¼ł
    -0.23
    pected
    -0.23
    POSITIVE LOGITS
    urn
    0.32
    Bay
    0.30
    /browse
    0.28
    ä¼ij
    0.28
     Bay
    0.28
    /*------------------------------------------------
    0.26
     mentioned
    0.25
    URN
    0.24
     resting
    0.24
    misc
    0.24
    Activations Density 0.003%

    No Known Activations