© 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. 31448
    Prev
    Next
    INDEX
    Explanations

    object graph

    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
    áz
    -0.06
    åĪ°è¿Ļ个
    -0.06
    ARD
    -0.06
    ÃŃg
    -0.06
    ardin
    -0.06
     ë¶ĢíĦ°
    -0.06
    VENT
    -0.06
    ard
    -0.06
    éĿĴé¾Ļ
    -0.06
    гÑĢÑĭ
    -0.06
    POSITIVE LOGITS
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    0.09
    uré
    0.08
    ple
    0.08
    עת
    0.07
     *.*
    0.07
    ÙĦد
    0.07
    skr
    0.07
    á»ģn
    0.07
    ystore
    0.07
    æĿ¥äºº
    0.07
    Activations Density 0.069%

    No Known Activations