© 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. 22795
    Prev
    Next
    INDEX
    Explanations

    risk factor

    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
     momentarily
    -0.07
    calar
    -0.06
    åĴĮè°IJ
    -0.06
    æŶèĢĮ
    -0.06
    æī§ä¸ļèį¯å¸Ī
    -0.06
     surface
    -0.06
     resolution
    -0.06
     coordinate
    -0.06
     harmony
    -0.06
    ¯
    -0.06
    POSITIVE LOGITS
     risk
    0.13
    é£İéĻ©
    0.12
    Risk
    0.11
    risk
    0.11
     Risk
    0.11
     ÑĢиÑģк
    0.11
     odds
    0.10
     Odds
    0.10
    åį±éĻ©
    0.10
    åį±éĻ©åĽłç´ł
    0.10
    Activations Density 0.284%

    No Known Activations