© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49654
    Prev
    Next
    INDEX
    Explanations

    `<!` followed by markup/code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ़
    -0.11
    ãĤĭãģ¨
    -0.10
    <|box_end|>
    -0.10
    ally
    -0.09
    åı¯æĥ³
    -0.09
    窿
    -0.09
    ие
    -0.09
    adecimal
    -0.09
    ussion
    -0.09
    urts
    -0.09
    POSITIVE LOGITS
    ÛĮ
    0.10
    ´
    0.10
    ia
    0.10
    s
    0.09
    人
    0.09
    äºĨ
    0.08
    ter
    0.07
    l
    0.07
    ä¸Ģ
    0.07
    ï¸İ
    0.07
    Activations Density 0.003%

    No Known Activations