© 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. 62629
    Prev
    Next
    INDEX
    Explanations

    options, list, assuming, original, curated

    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
    etest
    -0.07
    ulam
    -0.07
     Weiner
    -0.07
    åij¨èº«
    -0.07
    /sbin
    -0.07
    ç´§
    -0.07
    tractor
    -0.06
    èĪ¬
    -0.06
    engers
    -0.06
    çī¹æ®ĬçļĦ
    -0.06
    POSITIVE LOGITS
    ÙĬارات
    0.07
     flexibil
    0.07
    wali
    0.07
    åĺ´
    0.06
    æĸĩ件精ç¥ŀ
    0.06
    utang
    0.06
    åºĶä¿ĿæĮģ
    0.06
    åIJĥå®Į
    0.06
    å±ķæľĽæľªæĿ¥
    0.06
    -backend
    0.06
    Activations Density 0.019%

    No Known Activations