© 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. 8309
    Prev
    Next
    INDEX
    Explanations

    quoted text 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
    ç®Ģ称
    -0.08
    尼奥
    -0.08
    以ä¸ĭç®Ģ称
    -0.06
    cern
    -0.06
     hefty
    -0.06
    æĸ°åĬłåĿ¡
    -0.06
    çıĬ
    -0.06
    鱿
    -0.06
    zza
    -0.06
    зма
    -0.06
    POSITIVE LOGITS
    åŃIJåĴĮ
    0.08
    occhi
    0.08
    ork
    0.08
    ogan
    0.08
    ordinate
    0.08
    omo
    0.08
    anny
    0.08
    ihak
    0.07
    çĽĬçĶŁ
    0.07
    ocal
    0.07
    Activations Density 1.259%

    No Known Activations