© 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. 18505
    Prev
    Next
    INDEX
    Explanations

    units of area and measurement

    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
    IFY
    -0.07
    igr
    -0.07
    çī¢çī¢æĬĬæı¡
    -0.07
    ä½ĵåĪ¶
    -0.07
    æ»ŀ
    -0.07
    erte
    -0.07
    åĮĸå·¥æľīéĻIJåħ¬åı¸
    -0.07
     bá»ķng
    -0.07
    uco
    -0.06
    Chain
    -0.06
    POSITIVE LOGITS
    acol
    0.08
    设å¤ĩä¸Ĭ
    0.08
     pores
    0.08
     surface
    0.07
    ÄĽ
    0.07
    orda
    0.07
    andr
    0.07
    ocz
    0.07
    olls
    0.07
     повеÑĢÑħноÑģÑĤÑĮ
    0.07
    Activations Density 0.005%

    No Known Activations