© 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. 57794
    Prev
    Next
    INDEX
    Explanations

    heedless, vindictive, gutsy, sexiness, piss-taking

    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
    ĻĤ
    -0.08
    водов
    -0.08
    URNS
    -0.07
    inage
    -0.07
    водÑĭ
    -0.07
    minos
    -0.07
    rema
    -0.07
    itionen
    -0.07
    TINGS
    -0.07
    SSERT
    -0.07
    POSITIVE LOGITS
    æĢ§çļĦ
    0.14
    ful
    0.13
    æĢ§åĴĮ
    0.13
    æĢ§åľ°
    0.12
    æĢ§ä¸İ
    0.12
    ìłģìĿ¸
    0.11
    æĢ§æĪĸ
    0.11
    æĢ§åıĬ
    0.11
    æĢ§
    0.11
    æĢ§æĺ¯
    0.11
    Activations Density 0.547%

    No Known Activations