© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20741
    Prev
    Next
    INDEX
    Explanations

    quaker, LESS, BC, Cube, Park

    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
    fulness
    -0.06
    æŀģå¯Į
    -0.06
     Rub
    -0.06
    åħ¶
    -0.06
     cl
    -0.06
    Âł
    -0.06
    rub
    -0.06
    m
    -0.06
    cb
    -0.05
     Wyatt
    -0.05
    POSITIVE LOGITS
    ÑĤоÑĢи
    0.08
     avvic
    0.08
    egger
    0.08
     chÄĥng
    0.08
    éĺ²ç©º
    0.08
    ák
    0.08
    sonian
    0.07
    eder
    0.07
    ìĸ´ëĤĺ
    0.07
    å¼ĢåĬ¨
    0.07
    Activations Density 0.014%

    No Known Activations