© 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. 24650
    Prev
    Next
    INDEX
    Explanations

    goal of

    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
    æĪijçŃī
    -0.08
    åľ°äºļ
    -0.07
    æĪijåħĪ
    -0.07
    æĪijçľĭ
    -0.07
    eca
    -0.07
     Commod
    -0.07
    ditor
    -0.06
    cobra
    -0.06
    ä¸įå¦Ĥ
    -0.06
    lator
    -0.06
    POSITIVE LOGITS
    yron
    0.08
    以ä¸ĬåĨħ容
    0.07
     übrigens
    0.07
    orre
    0.07
    bruck
    0.07
     ìĿ´ì²ĺëŁ¼
    0.07
    å¾Īæ¸ħæ¥ļ
    0.07
    åĴ¨è¯¢çĥŃ线
    0.07
    åĭĿæīĭ
    0.06
    åIJįåī¯åħ¶å®ŀçļĦ
    0.06
    Activations Density 0.002%

    No Known Activations