© 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. 1307
    Prev
    Next
    INDEX
    Explanations

    url or path delimiter

    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
    ↵
    -0.07
    ,
    -0.07
    -0.05
     Glo
    -0.05
     when
    -0.05
    -controls
    -0.05
    RITE
    -0.05
    æ¸ħæľĿ
    -0.05
    Ùı
    -0.05
    rite
    -0.05
    POSITIVE LOGITS
    群çļĦ
    0.10
    ubu
    0.09
     ÐŁÐ¾Ð¿ÑĢо
    0.08
     ÐĴедÑĥ
    0.08
    身临åħ¶å¢ĥ
    0.08
    âĹĩâĹĨ
    0.08
    _locator
    0.08
     ÐĴÑģÑĤÑĢе
    0.08
    äºĭåįĬåĬŁåĢį
    0.08
    łĢ
    0.08
    Activations Density 0.172%

    No Known Activations