© 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. 61277
    Prev
    Next
    INDEX
    Explanations

    names and URLs

    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
    .blogspot
    -0.09
    @gmail
    -0.08
    .com
    -0.07
    uari
    -0.07
    Renderer
    -0.07
    æĸĭ
    -0.07
    .appspot
    -0.07
    @yahoo
    -0.07
    @hotmail
    -0.06
    à¹Į
    -0.06
    POSITIVE LOGITS
    cato
    0.07
    çĻ¾åĪĨçĻ¾
    0.07
    acor
    0.07
    ÑĢев
    0.07
    ELD
    0.07
    æĤį
    0.07
    ify
    0.07
    zysta
    0.07
    好礼
    0.07
    ÑĢем
    0.07
    Activations Density 0.547%

    No Known Activations