© 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. 32041
    Prev
    Next
    INDEX
    Explanations

    safety and caution

    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
    åħ´
    -0.09
    以轻
    -0.08
    -hooks
    -0.08
    èĪĪ
    -0.08
    cko
    -0.08
    个åŃ©åŃIJ
    -0.07
    ymous
    -0.07
    çĽ¼æľĽ
    -0.07
    webs
    -0.07
    regor
    -0.07
    POSITIVE LOGITS
    å®ģåı¯
    0.10
     unnecessarily
    0.10
     paranoid
    0.09
    åĨĹä½Ļ
    0.09
    ä¿Ŀå®Ī
    0.09
     safety
    0.09
     protective
    0.09
     generously
    0.09
    å®īåħ¨
    0.09
    æĽ´å®īåħ¨
    0.08
    Activations Density 0.091%

    No Known Activations