© 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. 62108
    Prev
    Next
    INDEX
    Explanations

    safe and harmlessness 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
    mey
    -0.09
    æīįèĥ½å®ŀçİ°
    -0.09
    imony
    -0.08
    anzo
    -0.08
    æīįèĥ½å¾ĹåĪ°
    -0.08
    åĪ»éª¨éĵŃ
    -0.08
    æīįèĥ½è®©
    -0.08
     slugg
    -0.08
    rim
    -0.08
     pobre
    -0.08
    POSITIVE LOGITS
    åı¯ä»¥æĶ¾å¿ĥ
    0.15
    æĶ¾å¿ĥ
    0.13
    å®īåħ¨
    0.12
    ä¸įä¼ļ对
    0.12
     safety
    0.12
    请æĶ¾å¿ĥ
    0.11
    ä¸įçĶ¨æĭħå¿ĥ
    0.11
    ä¸įä¼ļ产çĶŁ
    0.11
     harmless
    0.11
     safe
    0.11
    Activations Density 0.215%

    No Known Activations