© 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. 32-TRANSCODER-HP
    7. 43996
    Prev
    Next
    INDEX
    Explanations

    HTML and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    奥æĸ¯åį¡
    -0.27
    abet
    -0.27
    енÑĤ
    -0.25
    ento
    -0.25
    åľ¨æ·±åľ³
    -0.25
    PERT
    -0.24
    é¬ĺ
    -0.24
    Ùĩب
    -0.24
    éĽª
    -0.24
    harma
    -0.24
    POSITIVE LOGITS
    alc
    0.28
    æĸ½
    0.28
     alc
    0.27
    ltr
    0.26
    alone
    0.26
    羣çĪ±
    0.25
    vir
    0.25
    ãģ°ãģĭãĤĬ
    0.24
    èĢĨ
    0.24
    isci
    0.24
    Activations Density 0.782%

    No Known Activations