© 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. 58205
    Prev
    Next
    INDEX
    Explanations

    HTML spacing and tags

    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
    acad
    -0.07
    çļĦéĩį大
    -0.07
    givning
    -0.07
    ãĥĶãĥĥãĤ¯
    -0.07
    ent
    -0.07
    andon
    -0.07
    миÑĢ
    -0.07
    มà¸ĩà¸Ħล
    -0.07
    ivil
    -0.06
    elige
    -0.06
    POSITIVE LOGITS
    ÑĪкой
    0.07
    unya
    0.07
    å©Ĩ
    0.07
    ÙĨÙĬÙģ
    0.07
    å±ŀäºİä½łçļĦ
    0.06
    æ³ķåŃIJ
    0.06
    lev
    0.06
    ÙĪÙĤÙĪÙģ
    0.06
    ager
    0.06
    åĿĹéĴ±
    0.06
    Activations Density 0.003%

    No Known Activations