© 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. 49733
    Prev
    Next
    INDEX
    Explanations

    I know that

    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
    æĪij认为
    -0.08
    æĪij们çľĭåĪ°
    -0.08
    认为
    -0.07
    认为æĺ¯
    -0.07
    以èĩ³äºİ
    -0.07
    æĪij建议
    -0.07
    åı¯è§ģ
    -0.07
     perceived
    -0.07
    æĪij们认为
    -0.07
    被认为
    -0.07
    POSITIVE LOGITS
    ä¹ŁçŁ¥éģĵ
    0.13
     pasti
    0.11
    è¿Ļ个éģĵçIJĨ
    0.09
    æĥħåĨµåIJİ
    0.09
    æľīå¾Īå¤ļ人
    0.08
    çļĦéģĵçIJĨ
    0.08
    äºĨä¸Ģå®ļ
    0.08
    è¦ģæĿ¥
    0.08
    å±ĢéĻIJæĢ§
    0.08
    ä¸Ģå®ļä¸įä¼ļ
    0.08
    Activations Density 0.465%

    No Known Activations