© 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. 60873
    Prev
    Next
    INDEX
    Explanations

    code comments and symbols

    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
    ESTA
    -0.08
    adini
    -0.08
    Îĸ
    -0.08
    lest
    -0.08
    çĪ¸çĪ¸çļĦ
    -0.08
    placeholders
    -0.07
     Ilmais
    -0.07
    struments
    -0.07
     lest
    -0.07
    usak
    -0.07
    POSITIVE LOGITS
    ar
    0.07
     Ara
    0.07
    为éĿŀ
    0.06
     Priv
    0.06
    aw
    0.06
    aum
    0.06
    arma
    0.06
    污水å¤ĦçIJĨ
    0.06
    天河
    0.06
    olec
    0.06
    Activations Density 0.514%

    No Known Activations