© 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. 63873
    Prev
    Next
    INDEX
    Explanations

    safety and risk assessment

    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
    izm
    -0.08
    丹éĿĴ
    -0.07
     eslint
    -0.07
    æķ°æį®ä¼łè¾ĵ
    -0.07
    åĭī
    -0.07
    èij¬
    -0.06
    Ø°Ùĩ
    -0.06
    顺çķħ
    -0.06
    Position
    -0.06
    æľĢå¿«çļĦ
    -0.06
    POSITIVE LOGITS
     safety
    0.10
    Safety
    0.09
     Safety
    0.09
    çļĦå®īåħ¨
    0.08
     protection
    0.08
    afety
    0.08
    ç¡®ä¿Ŀå®īåħ¨
    0.07
     conservatism
    0.07
    å®īåħ¨
    0.07
    adal
    0.07
    Activations Density 0.002%

    No Known Activations