© 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. 19207
    Prev
    Next
    INDEX
    Explanations

    names following titles or events

    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
    çŁ¾
    -0.07
    éĿłè°±
    -0.07
    å§ĭèĩ³
    -0.07
    ãģªãĤĬãģ«
    -0.07
    ottom
    -0.07
    å¾ĹçĽĬ
    -0.07
    å¯ĦãģĽ
    -0.07
    æ¶Ī磨
    -0.06
    注æĦıåĪ°äºĨ
    -0.06
    æŁĦ
    -0.06
    POSITIVE LOGITS
     bá»ĭ
    0.09
    æľīä»·åĢ¼çļĦ
    0.09
     unprotected
    0.08
    æŃ»äºİ
    0.08
    çļĦ被
    0.08
     khá»ıi
    0.08
    被åĪ¤
    0.08
    å¿ĥçĪ±çļĦ
    0.08
    æĹłè¾ľ
    0.08
    æĹłæķħ
    0.08
    Activations Density 0.527%

    No Known Activations