© 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. 62435
    Prev
    Next
    INDEX
    Explanations

    now

    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
    æѤåīįçļĦ
    -0.08
    inker
    -0.08
    ä¸įæĽ¾
    -0.08
     last
    -0.08
    ä»İæĿ¥æ²¡æľī
    -0.07
    Å¡k
    -0.07
    æĪijæĽ¾
    -0.07
    æĪij们没æľī
    -0.07
    åį´å§ĭç»Ī
    -0.07
    ä»İæĿ¥æ²¡
    -0.07
    POSITIVE LOGITS
    here
    0.08
    为æŃ¢
    0.07
    æŃ£å¤Ħäºİ
    0.07
    ä¹ĭ计
    0.07
    çŃīæĥħåĨµ
    0.07
    段çļĦ
    0.07
    çļĦæĥħåĨµ
    0.07
    段éļİ
    0.07
    ê¹Įì§Ģ
    0.06
     sekarang
    0.06
    Activations Density 0.108%

    No Known Activations