© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30431
    Prev
    Next
    INDEX
    Explanations

    variables in equations

    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
    磨éļ¾
    -0.08
    äºĭ件
    -0.07
    abor
    -0.07
    vorg
    -0.07
    äºĭ件çļĦ
    -0.07
    éĢłèĪ¹
    -0.07
    Than
    -0.07
    幸
    -0.07
    é¦ģ
    -0.07
    äºĭ件ä¸Ń
    -0.06
    POSITIVE LOGITS
     outright
    0.07
    wor
    0.06
    alaman
    0.06
    диÑĤелÑĮ
    0.06
    elih
    0.06
    ç»ĵåIJĪå®ŀéĻħ
    0.06
    inesi
    0.06
    è¯Ĩ
    0.06
    çĭ¬ç§Ģ
    0.06
    angers
    0.06
    Activations Density 0.014%

    No Known Activations