© 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. 49604
    Prev
    Next
    INDEX
    Explanations

    according to reports and statistics

    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
    skr
    -0.08
    å·¥ä½ľè¿Ľè¡ĮäºĨ
    -0.08
    <|box_end|>
    -0.08
    à¸ij
    -0.08
    achable
    -0.07
    peg
    -0.07
    дове
    -0.07
    ãģĿãģĵãģ§
    -0.07
    jenigen
    -0.07
    .utf
    -0.07
    POSITIVE LOGITS
     ÙģØ¥ÙĨ
    0.10
    èµĦæĸĻæĺ¾ç¤º
    0.08
    并ç»ı
    0.07
    ï¼ĮãĢĬ
    0.07
    ï¼Į“
    0.06
    ãģ«ãĤĪãĤĭãģ¨
    0.06
     ëĶ°ë¥´ë©´
    0.06
    оÑģÑĮ
    0.06
    aniem
    0.06
    ãģ«ãĤĪ
    0.06
    Activations Density 0.380%

    No Known Activations