© 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. 24-TRANSCODER-HP
    7. 149390
    Prev
    Next
    INDEX
    Explanations

    unique words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    缮ãģ«
    -0.29
    istan
    -0.27
    [val
    -0.26
    åŤ
    -0.26
    aho
    -0.26
    æľĢå°ij
    -0.24
     Elk
    -0.24
    heels
    -0.24
    }while
    -0.24
     Contest
    -0.23
    POSITIVE LOGITS
    æ°ijéĹ´
    0.28
    odie
    0.27
    lers
    0.26
    athing
    0.24
    à¸Ľà¸£à¸°
    0.24
    æݪ
    0.23
    obic
    0.23
    .kind
    0.23
    escape
    0.23
     emb
    0.23
    Activations Density 0.302%

    No Known Activations