© 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. 56882
    Prev
    Next
    INDEX
    Explanations

    insoluble / soluble

    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
    æĻļäºĨ
    -0.07
    ç´łé¢ľ
    -0.07
    å¾ģ
    -0.07
    ÑĤеле
    -0.07
    oplan
    -0.07
    ossi
    -0.07
    здо
    -0.06
    uschen
    -0.06
    arend
    -0.06
    è¨Ĺ
    -0.06
    POSITIVE LOGITS
    æ°´æĢ§
    0.08
    isoft
    0.08
    edia
    0.08
    溶æĢ§
    0.07
    à§Ģয়
    0.07
    /misc
    0.07
    odia
    0.07
    äºĶ大
    0.07
    uble
    0.07
    _Exception
    0.07
    Activations Density 0.008%

    No Known Activations