© 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. 111276
    Prev
    Next
    INDEX
    Explanations

    Assorted text

    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
    olec
    -0.29
     Supporting
    -0.26
    æľĭåıĭ们
    -0.26
    arkan
    -0.26
    ulant
    -0.25
    ulsive
    -0.24
    Friends
    -0.24
    akin
    -0.24
     Lamar
    -0.24
    ä¿Ŀå®Ī
    -0.24
    POSITIVE LOGITS
    à¸Ĺà¸Ńà¸ĩ
    0.27
    CLS
    0.26
    åijĬ
    0.26
     person
    0.26
    .cgi
    0.26
    qus
    0.25
    è¶Ĭè¿ĩ
    0.25
     sterile
    0.25
    Person
    0.25
    iren
    0.24
    Activations Density 0.017%

    No Known Activations