© 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. 30414
    Prev
    Next
    INDEX
    Explanations

    capability leader

    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
    mad
    -0.08
    è¿Ļ说æĺİ
    -0.07
     paran
    -0.07
    Rather
    -0.07
    λια
    -0.07
    Fortunately
    -0.07
    æĥ«
    -0.07
    å¼łèī¯
    -0.06
    ycop
    -0.06
    fv
    -0.06
    POSITIVE LOGITS
    容æĺĵ导èĩ´
    0.11
    容æĺĵéĢłæĪIJ
    0.10
    åı¯èĥ½ä¼ļ导èĩ´
    0.10
    容æĺĵå¼ķèµ·
    0.09
    ä¸įåĪ©äºİ
    0.09
     risk
    0.09
    ä¸įåIJĪéĢĤ
    0.09
    ä¼ļéĢłæĪIJ
    0.09
    åı¯èĥ½å¯¼èĩ´
    0.09
    åı¯èĥ½éĢłæĪIJ
    0.08
    Activations Density 0.138%

    No Known Activations