© 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. 38302
    Prev
    Next
    INDEX
    Explanations

    end of sentence or question

    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
    åı¯æĢľ
    -0.06
    åıªæĺ¯ä¸Ģç§į
    -0.06
    åĬłå·¥
    -0.06
    à¸Ĺาà¸ĩà¸ģาร
    -0.06
    ...”
    -0.06
    åıªå¾Ĺ
    -0.06
     damaged
    -0.06
    åı¯æĢľçļĦ
    -0.06
    äºļå½ĵ
    -0.06
    éģŃåıĹ
    -0.06
    POSITIVE LOGITS
    Explanation
    0.08
    icht
    0.08
    äººä¸ºæľ¬
    0.08
    çŃĶæ¡Ī解æŀIJ
    0.08
    æĪ·æĻĵ
    0.08
    äºĨ解ä¸ĭ
    0.08
     explanation
    0.08
     Explanation
    0.07
    æľī家
    0.07
     Erklärung
    0.07
    Activations Density 0.014%

    No Known Activations