© 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. 20-TRANSCODER-HP
    7. 62575
    Prev
    Next
    INDEX
    Explanations

    URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çľ¼åīį
    -0.28
    alse
    -0.26
    æ´Ĺ
    -0.26
     mắt
    -0.25
     setting
    -0.25
    DO
    -0.25
    mayı
    -0.24
    confirm
    -0.24
    åįı
    -0.24
    ãģ°
    -0.24
    POSITIVE LOGITS
    ç¿©
    0.26
     virgin
    0.26
    caller
    0.25
    Enlarge
    0.25
    kah
    0.25
    åŁºæľ¬æĥħåĨµ
    0.23
     porr
    0.23
     תש
    0.23
    ahi
    0.23
    TestMethod
    0.23
    Activations Density 1.836%

    No Known Activations