© 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. 63167
    Prev
    Next
    INDEX
    Explanations

    proof questions

    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
    aggi
    -0.07
     Geme
    -0.07
    ween
    -0.06
    æľīæīĢ
    -0.06
    ileo
    -0.06
     ÑıкобÑĭ
    -0.06
    eshire
    -0.06
    ses
    -0.06
    ubre
    -0.06
    请åĬ¡å¿ħ
    -0.06
    POSITIVE LOGITS
    æľĢ缴æİ¥
    0.09
     either
    0.08
    æľĢæľīæķĪ
    0.08
    æĸ¹æ³ķæĺ¯
    0.08
    æĪij们åı¯ä»¥éĢļè¿ĩ
    0.08
     approach
    0.08
    ä½ĻåĬĽ
    0.07
     Approach
    0.07
    çĤºæѤ
    0.07
    æĸ¹æ³ķè¿Ľè¡Į
    0.07
    Activations Density 0.061%

    No Known Activations