© 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. 30-TRANSCODER-HP
    7. 95979
    Prev
    Next
    INDEX
    Explanations

    it

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä»ĸ们ä¼ļ
    -0.39
    ä½łåı¯ä»¥
    -0.37
    æĤ¨åı¯ä»¥
    -0.37
    æĪij们ä¼ļ
    -0.36
    ä½łéľĢè¦ģ
    -0.36
    æĪij们åı¯ä»¥
    -0.33
    ä½łä¼ļ
    -0.31
    ãģĻãĤĭãģĵãģ¨ãģĮãģ§ãģįãģ¾ãģĻ
    -0.31
    ä¹Łåı¯ä»¥
    -0.30
    ä½łåºĶ该
    -0.30
    POSITIVE LOGITS
    bur
    0.32
    UGIN
    0.28
     mình
    0.26
    å²³
    0.24
     Milan
    0.23
    å¶
    0.23
     honored
    0.23
    ios
    0.23
     há»ĵ
    0.23
     Hip
    0.22
    Activations Density 1.030%

    No Known Activations