© 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. 129234
    Prev
    Next
    INDEX
    Explanations

    by

    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
    ports
    -0.32
    åijĬè¯ī大家
    -0.28
    limits
    -0.27
     OPS
    -0.27
    vara
    -0.26
    好åIJ§
    -0.26
    交éĢļè¿IJè¾ĵ
    -0.26
    客æĪ·æıIJä¾Ľ
    -0.25
     ORD
    -0.25
    DOT
    -0.25
    POSITIVE LOGITS
    groupid
    0.28
    çģŃ
    0.27
     triangle
    0.26
    çģĮ
    0.26
    ghi
    0.26
    ohn
    0.25
     indicated
    0.25
     combination
    0.24
     particular
    0.24
     jointly
    0.24
    Activations Density 0.019%

    No Known Activations