© 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. 28377
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
    å°Ķåħĭ
    -0.09
    åIJĮåı·
    -0.07
    èº
    -0.07
    ç½ijé¦ĸ页
    -0.07
    åIJİèĢħ
    -0.06
     заÑħ
    -0.06
    .forName
    -0.06
    èĻ½å°ı
    -0.06
     ols
    -0.06
    èĥ½å¤Łè®©
    -0.06
    POSITIVE LOGITS
    bell
    0.08
    æĸ°åŁİ
    0.07
    åŃ£
    0.07
    åŃ£çļĦ
    0.07
    äºİä»Ĭå¹´
    0.07
    éĻĢèŀº
    0.07
    ERIC
    0.07
    æ´²
    0.07
    λÏĮ
    0.07
    åŃ½
    0.07
    Activations Density 0.026%

    No Known Activations