© 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. 32195
    Prev
    Next
    INDEX
    Explanations

    markup and code structures

    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
    seek
    -0.08
    oids
    -0.08
    æ±Ĥæĺ¯
    -0.08
    ä¸ŃåĽ½éĿĴå¹´
    -0.08
    ä¼ĺ
    -0.08
    à§ģষ
    -0.07
    lettes
    -0.07
    åľ¨è¢«
    -0.07
    å¾ĹçĽĬ
    -0.07
    odin
    -0.07
    POSITIVE LOGITS
    åĽºå®ļ
    0.07
     separating
    0.07
     fixed
    0.07
    acker
    0.06
    kas
    0.06
    约å®ļçļĦ
    0.06
    å¤ļæĿ¡
    0.06
    acar
    0.06
    è¿ĻæĿ¡
    0.06
    åĽºå®ļçļĦ
    0.06
    Activations Density 0.004%

    No Known Activations