© 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. 62683
    Prev
    Next
    INDEX
    Explanations

    -style license

    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
    æĪijçļĦ书æŀ¶
    -0.08
    æĸ¹éĿ¢
    -0.08
    代表æĢ§çļĦ
    -0.07
    ary
    -0.07
     mari
    -0.07
    ä¹ĭç¥ŀ
    -0.07
    æĹ¶ä»£
    -0.07
    راÙĨ
    -0.07
    ίκ
    -0.07
    ä¸ĢèĪ¬æĿ¥è¯´
    -0.07
    POSITIVE LOGITS
    严
    0.07
     Buckley
    0.07
    ensor
    0.06
    åļ´
    0.06
    anguard
    0.06
    borg
    0.06
    éĽ¯
    0.06
    tricos
    0.06
    补缺
    0.06
    ä¸įæĥ§
    0.06
    Activations Density 0.005%

    No Known Activations