© 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. 57823
    Prev
    Next
    INDEX
    Explanations

    file paths/code snippets

    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
    æĸĩåĮĸåĴĮ
    -0.27
    iner
    -0.27
    è´¸æĺĵ
    -0.25
    æ²»çIJĨä½ĵç³»
    -0.25
    åķĨè´¸
    -0.25
    交æİ¥
    -0.25
    anted
    -0.24
    ãģ³
    -0.24
    _/
    -0.24
    å®ı
    -0.24
    POSITIVE LOGITS
    åŃĺåľ¨ä¸Ģå®ļ
    0.26
    Elim
    0.26
    .UnitTesting
    0.26
    даÑİÑĤ
    0.26
    åIJĥå¾Ĺ
    0.26
     elim
    0.26
    ;č↵č↵č↵
    0.25
    еж
    0.25
     addAction
    0.24
    ycastle
    0.24
    Activations Density 0.001%

    No Known Activations