© 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. 41417
    Prev
    Next
    INDEX
    Explanations

    adjective/jectives

    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
    heds
    -0.09
    abouts
    -0.09
    Ñīенко
    -0.08
    igh
    -0.08
    áĢŀáĢ°
    -0.08
    ä¸Ĭ人
    -0.07
    sä
    -0.07
    isman
    -0.07
    æĹłéĺ»
    -0.07
    ä¸Ń磩
    -0.07
    POSITIVE LOGITS
    -turned
    0.08
    pell
    0.08
    åĴĮè¡ĮåĬ¨
    0.07
    unner
    0.07
    åĴĮè¡Į为
    0.07
    ваÑĢ
    0.07
    æĺ¯çĶ¨æĿ¥
    0.07
    ifiable
    0.07
    abetic
    0.06
    rawl
    0.06
    Activations Density 0.011%

    No Known Activations