© 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. 63372
    Prev
    Next
    INDEX
    Explanations

    public: access specifier

    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
    acci
    -0.07
    ç·
    -0.07
    worth
    -0.07
    esp
    -0.07
    μι
    -0.07
    ivin
    -0.06
    ä½ķåħ¶
    -0.06
    ERG
    -0.06
    çĶ³æĺİ
    -0.06
    æľºæĻº
    -0.06
    POSITIVE LOGITS
    дина
    0.08
    ustu
    0.08
    è¿ľæµģ
    0.07
    åŁ¹åħ»å¹¼åĦ¿
    0.07
    åѦåłĤ
    0.07
    Continue
    0.07
    å°ĨæĿ¥çļĦ
    0.07
    åĽłäºº
    0.07
    æľ¨æĸ¯
    0.07
    éľĢè¦ģæĪij们
    0.06
    Activations Density 0.002%

    No Known Activations