© 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. 22692
    Prev
    Next
    INDEX
    Explanations

    parentheses and closing punctuation

    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
    .mit
    -0.08
    ÙĪرÙĬا
    -0.07
    èĪİ
    -0.07
    æķĻäºİ
    -0.07
    衬衣
    -0.07
    shirt
    -0.07
     ЯнваÑĢ
    -0.07
    atically
    -0.07
    urgia
    -0.07
    ä¿Ŀéļľå·¥ä½ľ
    -0.07
    POSITIVE LOGITS
     cach
    0.06
    éģĩ
    0.06
    éģĩä¸Ĭ
    0.06
    æĹłæķĪçļĦ
    0.06
    èĢĮåĩº
    0.06
    -main
    0.06
     loose
    0.06
    åľ¨å½ĵåľ°
    0.06
    asn
    0.06
    éģĩè§ģ
    0.06
    Activations Density 0.010%

    No Known Activations