© 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. 56160
    Prev
    Next
    INDEX
    Explanations

    second derivative of

    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
    دÙĬÙĨ
    -0.07
    ç«ĭãģ¦
    -0.07
    ׳×Ļ×Ļ×Ŀ
    -0.07
    ົ
    -0.07
    Parsed
    -0.07
    éģİå¤ļ
    -0.06
    踢
    -0.06
    ç§ij夫
    -0.06
    _Enter
    -0.06
    åĵ
    -0.06
    POSITIVE LOGITS
    EMON
    0.09
     Blanco
    0.07
    lege
    0.07
    çļĦ综åIJĪ
    0.07
    æķ£
    0.06
    æī¾åĪ°èĩªå·±çļĦ
    0.06
    Svg
    0.06
    çļĨçŁ¥
    0.06
    ellow
    0.06
     containing
    0.06
    Activations Density 0.078%

    No Known Activations