© 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. 8697
    Prev
    Next
    INDEX
    Explanations

    specific settings and descriptions

    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
    umbo
    -0.07
    èĤ¯å®ļ
    -0.07
    spa
    -0.07
    çļĦç¡®æĺ¯
    -0.07
    çļĦç¡®
    -0.07
    åĨįåĪ°
    -0.07
    Ãłnh
    -0.06
    ?action
    -0.06
     Galleria
    -0.06
    åĨįæĢİä¹Ī
    -0.06
    POSITIVE LOGITS
    éĢļè¿ĩè¿ĻäºĽ
    0.08
     rather
    0.07
    æĭīåħĭ
    0.07
    èĢĮéĿŀ
    0.07
    arli
    0.07
    èĢĮä¸įæĺ¯
    0.07
    ä¸Ĭè¿Ľ
    0.07
    rather
    0.07
    ä¸Ķåħ·æľī
    0.07
    anty
    0.07
    Activations Density 0.789%

    No Known Activations