© 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. 19912
    Prev
    Next
    INDEX
    Explanations

    your, Your, MY, OUR, Custom

    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
    undu
    -0.08
    ushman
    -0.07
    سÙĤ
    -0.07
    çĺ¾
    -0.07
    ×ķ×ijר
    -0.07
    adt
    -0.07
    æµ®äºij
    -0.07
    è¡£èįī
    -0.07
    ywa
    -0.07
    é¬ĵ
    -0.06
    POSITIVE LOGITS
    innan
    0.07
    logic
    0.06
    ellas
    0.06
    _ATOMIC
    0.06
    åıijçĶŁæĶ¹åıĺ
    0.06
    perse
    0.06
    éĹ®é¢ĺåĴĮ
    0.06
    lyn
    0.06
    åľ¨éĩĮéĿ¢
    0.06
    pers
    0.06
    Activations Density 0.006%

    No Known Activations