© 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. 60866
    Prev
    Next
    INDEX
    Explanations

    baby boy

    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
    odob
    -0.07
    ritt
    -0.07
    adecimal
    -0.07
    вена
    -0.06
    {}".
    -0.06
    {}'.
    -0.06
    æĸ°åĬłåĿ¡
    -0.06
    {}",
    -0.06
    è·¯éĢı
    -0.06
    holm
    -0.06
    POSITIVE LOGITS
    çŁ¥ä¹ĭ
    0.09
    笹
    0.08
    æ¸ł
    0.08
    å±±ä¹ĭ
    0.07
    боÑĢа
    0.07
    ç«£
    0.07
    æ±Ŀ
    0.07
    -*-
    0.07
    TypeID
    0.07
    ./.
    0.07
    Activations Density 0.114%

    No Known Activations