© 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. 48127
    Prev
    Next
    INDEX
    Explanations

    ordering numbers

    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
    åĩĭ
    -0.08
    uth
    -0.07
    ä¸Ģæĸ°
    -0.07
    CONTENT
    -0.07
    àºŃ
    -0.07
    lag
    -0.07
    åĽ¢ç»ĵåįıä½ľ
    -0.06
     ÑģоÑģÑĤ
    -0.06
    ืà¸Ńà¸ĩ
    -0.06
    edel
    -0.06
    POSITIVE LOGITS
    æķ´
    0.09
    qry
    0.08
    ARS
    0.08
    æķ´æķ°
    0.07
    åıĮé±¼
    0.07
    åĽĽåĪĨ
    0.07
    书éĿ¢å½¢å¼ı
    0.07
    åĩłåĪĨ
    0.07
     Fraction
    0.07
    åħŃçĻ¾
    0.07
    Activations Density 0.018%

    No Known Activations