© 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. 26237
    Prev
    Next
    INDEX
    Explanations

    of the

    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
    неÑĤа
    -0.07
    .uni
    -0.07
    æĺ¯ä¸Ģå¥Ĺ
    -0.06
    Outline
    -0.06
    ä¸Ģå¥Ĺ
    -0.06
    rough
    -0.06
    çļĦä¸Ģå¥Ĺ
    -0.06
    enger
    -0.06
    åľ¨åħ¶ä¸Ń
    -0.06
    ellis
    -0.06
    POSITIVE LOGITS
    éĩij森
    0.08
    ÙĪغ
    0.08
    !==
    0.07
    obar
    0.07
    }):
    0.07
    stes
    0.06
    ä½Ĩæĺ¯çİ°åľ¨
    0.06
    (('
    0.06
    ÑĤÑĮе
    0.06
    axter
    0.06
    Activations Density 0.005%

    No Known Activations