© 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. 61608
    Prev
    Next
    INDEX
    Explanations

    lists.partGacancerextra

    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
    姬
    -0.07
     INDONESIA
    -0.07
    oba
    -0.07
    éĿ¢ç§¯çº¦
    -0.07
    iny
    -0.06
    ç«ŀæĬĢåľº
    -0.06
    ecure
    -0.06
    éĢĹ
    -0.06
    空ä¸Ń
    -0.06
    å¼ķ
    -0.06
    POSITIVE LOGITS
    lak
    0.08
    çĬ¯éĶĻ
    0.08
     pylint
    0.07
    ç©«
    0.07
    -fetch
    0.07
    peq
    0.07
    å·´å¡ŀ
    0.07
    erra
    0.07
    夫åŃIJ
    0.07
    pec
    0.07
    Activations Density 0.001%

    No Known Activations