© 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. 41528
    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
    åIJ¦åĪĻä¼ļ
    -0.08
    ergestellt
    -0.07
    ×Ļ×Ŀ
    -0.07
    te
    -0.07
    çĦ¶å¤§
    -0.07
     thereof
    -0.07
    åĻ¨
    -0.07
    vents
    -0.06
    å«£
    -0.06
    à¤Ī
    -0.06
    POSITIVE LOGITS
    éĹ®é¢ĺæĿ¥äºĨ
    0.11
    å¦ĤæŀľæĪij
    0.08
    对äºİéĤ£äºĽ
    0.08
    对äºİä¸Ģ个
    0.08
    è¿Ļ并ä¸įæĺ¯
    0.08
    ahi
    0.08
    etheless
    0.08
    åı¦ä¸Ģæĸ¹éĿ¢
    0.08
    ä¸ĢèĪ¬èĢĮè¨Ģ
    0.08
    rir
    0.08
    Activations Density 0.009%

    No Known Activations