© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64140
    Prev
    Next
    INDEX
    Explanations

    works correctly

    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
    éĿĴæ¢ħ
    -0.08
    è¶Ĭ
    -0.07
    xCD
    -0.07
    èĻ½çĦ¶æĪij
    -0.07
    abay
    -0.07
    çİ°çĬ¶
    -0.07
    è¶Ĭå¤ļ
    -0.07
    _drvdata
    -0.07
    äºĮ段
    -0.07
    符åIJĪ
    -0.07
    POSITIVE LOGITS
    ãģĵãģ¡ãĤīãģ¯
    0.07
    ä¹Łä¸įåIJĮ
    0.07
     Augusta
    0.07
    akov
    0.07
    instead
    0.07
    acher
    0.07
    æīįæĺ¯çľŁæŃ£çļĦ
    0.07
    steller
    0.06
    æł¡èĬ±
    0.06
     invece
    0.06
    Activations Density 0.010%

    No Known Activations