© 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. 55325
    Prev
    Next
    INDEX
    Explanations

    statements and claims

    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
     remont
    -0.09
    veje
    -0.09
    AZY
    -0.09
     <",
    -0.08
    TickCount
    -0.08
    emming
    -0.08
    ä¿ĬæĿ°
    -0.08
    avl
    -0.08
    lox
    -0.08
    æĭŃ缮
    -0.08
    POSITIVE LOGITS
    éĻĪè¿°
    0.08
    äºĭå®ŀ
    0.07
     presumed
    0.07
    ive
    0.07
    认å®ļäºĭå®ŀ
    0.06
     ÑĥÑĤвеÑĢ
    0.06
     statement
    0.06
     Prem
    0.06
    å¼ı
    0.06
     premise
    0.06
    Activations Density 0.015%

    No Known Activations