© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 58016
    Prev
    Next
    INDEX
    Explanations

    Ad, Ed, or Att

    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
    islation
    -0.28
    iswa
    -0.27
    追éļı
    -0.26
    æĻ®
    -0.25
    ä¸ĢåŃĹ
    -0.25
    æİ¥åıĹäºĨ
    -0.24
    æĥ³èµ·äºĨ
    -0.24
    绣
    -0.24
    /Index
    -0.23
    çek
    -0.23
    POSITIVE LOGITS
    ormap
    0.26
    lá
    0.25
    arkin
    0.25
    ç»ĪçĶŁ
    0.24
    ariat
    0.24
    é¢Ļ
    0.24
    å²ĺ
    0.24
    dating
    0.23
    pair
    0.23
    emes
    0.23
    Activations Density 0.013%

    No Known Activations