© 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. 27-TRANSCODER-HP
    7. 58339
    Prev
    Next
    INDEX
    Explanations

    Social

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dc
    -0.28
    åıĤåĬłä¼ļè®®
    -0.27
    横åIJij
    -0.25
    æľ¯è¯Ń
    -0.25
     rc
    -0.25
    encoder
    -0.25
    .rc
    -0.25
    å¿ĥåĬ¨
    -0.24
    _RC
    -0.24
     bag
    -0.24
    POSITIVE LOGITS
    /cop
    0.30
    mol
    0.29
    çİĭèĢħ
    0.29
    çªĿ
    0.28
    æĹºçĽĽ
    0.27
    åı¼
    0.27
    éĩİ
    0.26
    åijµæĬ¤
    0.26
    elper
    0.26
     mol
    0.26
    Activations Density 0.003%

    No Known Activations