© 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. 4360
    Prev
    Next
    INDEX
    Explanations

    male humans and animals

    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
    ç¼ĵåĴĮ
    -0.08
    ä¹ħä¹ħ
    -0.07
    ç·©
    -0.07
    aint
    -0.07
    åĵªæĢķæĺ¯
    -0.07
    èĢIJåĬĽ
    -0.07
    ÑģÑĤаÑı
    -0.07
     اÙĦتÙĩد
    -0.07
    å¹¿åľºèĪŀ
    -0.07
    enc
    -0.07
    POSITIVE LOGITS
     unprotected
    0.08
    缴æİ¥ä¸İ
    0.08
    apons
    0.07
     singleton
    0.07
     direct
    0.07
    缴æİ¥
    0.07
    /single
    0.07
    singleton
    0.07
    åĽ±
    0.07
    æļ´éľ²åľ¨
    0.07
    Activations Density 0.003%

    No Known Activations