© 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. 24652
    Prev
    Next
    INDEX
    Explanations

    vagueness and imprecision

    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
    ä¸įå®Į
    -0.09
    зва
    -0.09
    æĺ¯å®Įåħ¨
    -0.07
     sebaliknya
    -0.07
    DROP
    -0.07
    åıªä¸įéģİ
    -0.07
    >(*
    -0.07
    çŀ©
    -0.07
    ụng
    -0.07
    .):
    -0.07
    POSITIVE LOGITS
    ä¸Ķä¸į
    0.09
    ä¸Ķ
    0.08
    èĢĮä¸Ķ
    0.08
    ä¸Ķåħ·æľī
    0.07
    angelo
    0.07
     moreover
    0.07
    ä¸Ķåľ¨
    0.07
    èĢĮä¸Ķåľ¨
    0.06
    utti
    0.06
     vague
    0.06
    Activations Density 0.019%

    No Known Activations