© 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. 47803
    Prev
    Next
    INDEX
    Explanations

    population

    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
    æĶ¶èĹıæľ¬ç«Ļ
    -0.08
    ppo
    -0.08
     Whilst
    -0.07
    æ·±åħ¥æµħ
    -0.07
    icao
    -0.07
    orts
    -0.07
    /extensions
    -0.07
     PPP
    -0.07
    Whilst
    -0.07
    icious
    -0.06
    POSITIVE LOGITS
    èĨĿ
    0.07
    .Encoding
    0.06
    lk
    0.06
    åŃĿ
    0.06
    EM
    0.06
    ularity
    0.06
    æĬ¡
    0.06
    ä¹ĭåĪ«
    0.06
    èĩªæĦ¿
    0.06
    åı¤å±ĭ
    0.06
    Activations Density 0.007%

    No Known Activations