© 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. 21413
    Prev
    Next
    INDEX
    Explanations

    layout attribute `useAutolayout`

    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
    upo
    -0.07
    uent
    -0.07
    æŀģ大
    -0.07
    chy
    -0.07
    æŀģ
    -0.06
    ordu
    -0.06
    اراÙĨ
    -0.06
    ä¸Ģ个éĹ®é¢ĺ
    -0.06
    à¦Łà¦¿
    -0.06
    ç¾ļ
    -0.06
    POSITIVE LOGITS
    è¡ĮäºĨ
    0.08
    عاÙħ
    0.07
    ä¸ĭ载使çĶ¨
    0.07
    äºijå³°
    0.07
    çı
    0.07
    ões
    0.07
    ieza
    0.07
    item
    0.07
    http
    0.07
    दà¥Ī
    0.07
    Activations Density 0.910%

    No Known Activations