© 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. 38868
    Prev
    Next
    INDEX
    Explanations

    end of code or list item

    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
    anom
    -0.08
    ordo
    -0.07
    ordin
    -0.07
    UBLISH
    -0.07
    æľ¬ç«ĻåĨħ容
    -0.06
    ORD
    -0.06
    atty
    -0.06
    alar
    -0.06
    çļĦåıij
    -0.06
    èĬĿ
    -0.06
    POSITIVE LOGITS
    lemi
    0.07
    ä¹Łåı¯ä»¥ä½¿çĶ¨
    0.07
     spiagg
    0.07
     confirmed
    0.07
    åIJįåī¯åħ¶å®ŀ
    0.06
    çĴ¨
    0.06
     usable
    0.06
    weile
    0.06
    zem
    0.06
    ç»ıåħ¸çļĦ
    0.06
    Activations Density 0.033%

    No Known Activations