© 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. 3555
    Prev
    Next
    INDEX
    Explanations

    powers and exponents

    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
    åħĭç¦ı
    -0.08
    atown
    -0.08
    oleon
    -0.08
    ebes
    -0.07
    å®Ŀé¾Ļ
    -0.07
    æĬĬåŃ¦ä¹ł
    -0.07
    /front
    -0.07
    çļĦéĽª
    -0.07
    alah
    -0.07
    oire
    -0.07
    POSITIVE LOGITS
    èĬ±èĬ±
    0.07
    egen
    0.07
    è·¨
    0.07
    OMO
    0.07
    åħĥ人æ°ijå¸ģ
    0.07
    ØŃاÙĦ
    0.07
    STS
    0.06
    è·¨åĮºåŁŁ
    0.06
    æĮĤåľ¨
    0.06
     replicated
    0.06
    Activations Density 0.002%

    No Known Activations