© 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. 43860
    Prev
    Next
    INDEX
    Explanations

    technical text

    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
    Not in Any Lists

    No Comments

    Negative Logits
     sil
    -0.27
    eli
    -0.27
    ılı
    -0.25
    è¢Ĥ
    -0.24
    æµį
    -0.24
    é¾Ħ
    -0.24
    æ²»
    -0.24
    ql
    -0.24
    rieving
    -0.23
    磨
    -0.23
    POSITIVE LOGITS
    èķ¨
    0.31
    éĽ¾
    0.27
    YST
    0.26
    ids
    0.26
    æĵį纵
    0.25
    cation
    0.25
    CCA
    0.25
     host
    0.25
    Ids
    0.24
    ä¸»æľº
    0.24
    Activations Density 0.002%

    No Known Activations