© 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. 25495
    Prev
    Next
    INDEX
    Explanations

    assigning result or output

    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
    ponsors
    -0.07
    ä¸įçĿĢ
    -0.07
    好ä¸į
    -0.07
    kün
    -0.07
    çŀ¬
    -0.07
    вай
    -0.07
    绣
    -0.06
    å«Į
    -0.06
    esa
    -0.06
    é½IJå¿ĥ
    -0.06
    POSITIVE LOGITS
    éŵ
    0.07
    ãģ¤ãĤĤãĤĬ
    0.07
    ÑĢÑİ
    0.07
    trut
    0.06
    hton
    0.06
    ebt
    0.06
    ÑĦаÑĢ
    0.06
    çIJ
    0.06
    setAttribute
    0.06
     appeals
    0.06
    Activations Density 0.001%

    No Known Activations