© 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. 28611
    Prev
    Next
    INDEX
    Explanations

    recovery time

    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
    èİĺ
    -0.09
     audiovis
    -0.08
    /../
    -0.08
    à®Łà®¿à®¯
    -0.08
    춤
    -0.08
    ubre
    -0.08
    ãĥĭãĤ¢
    -0.08
    genza
    -0.08
    ä¸Ģè·³
    -0.08
    redo
    -0.08
    POSITIVE LOGITS
     tang
    0.07
     intercepted
    0.07
    angnya
    0.07
    ihar
    0.06
    æķ£
    0.06
    交
    0.06
    æ²¼
    0.06
     proportional
    0.06
    ough
    0.06
     centroid
    0.06
    Activations Density 0.003%

    No Known Activations