© 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. 9957
    Prev
    Next
    INDEX
    Explanations

    since, leap year

    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
     Cro
    -0.08
    åIJĦåħ·
    -0.07
    çľĭå¾Ĺ
    -0.07
    ÑĢоÑı
    -0.06
    åIJĦè¡Į
    -0.06
    å½ĵ好
    -0.06
    곤
    -0.06
    óa
    -0.06
    è¾ĵç»Ļ
    -0.06
    renz
    -0.06
    POSITIVE LOGITS
    å±ŀäºİ
    0.08
     neither
    0.08
    æľ¬å·¥ç¨ĭ
    0.07
    èĻ½çĦ¶æľī
    0.07
    éĩĩçĶ¨çļĦæĺ¯
    0.07
    çķ¥
    0.07
    adt
    0.07
    æĺ¯éĿŀ
    0.07
    åĨµ
    0.07
    屬æĸ¼
    0.07
    Activations Density 0.045%

    No Known Activations