© 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. 29412
    Prev
    Next
    INDEX
    Explanations

    quantifier order

    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
    jure
    -0.07
    upert
    -0.07
    zza
    -0.07
    ä¼ģ
    -0.07
    èµ°é«ĺ
    -0.06
    空ä¸Ń
    -0.06
     Cunning
    -0.06
    pen
    -0.06
    表éĿ¢ä¸Ĭ
    -0.06
    åĨ²
    -0.06
    POSITIVE LOGITS
    ÑĥÑīеÑģÑĤво
    0.09
    ÛĮت
    0.08
    æ½Ń
    0.08
    Æ¡
    0.08
    ıb
    0.07
    ä¸įåıĬ
    0.07
    ubr
    0.07
    andro
    0.07
     relationships
    0.07
    Äįiu
    0.07
    Activations Density 0.001%

    No Known Activations