© 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. 40954
    Prev
    Next
    INDEX
    Explanations

    flow, al, or, (

    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
    eland
    -0.07
    ç¼Ń
    -0.07
    æĢİä¹ĪåĬŀåij¢
    -0.06
    å²ģå²ģ
    -0.06
    æĢİä¹ĪåĬŀ
    -0.06
    acie
    -0.06
    ä¸įåıĤåĬł
    -0.06
    ingss
    -0.06
    alay
    -0.06
    æѦç¥ŀ
    -0.06
    POSITIVE LOGITS
    -based
    0.13
    -Based
    0.12
    based
    0.10
    [email
    0.09
    常çĶ¨äºİ
    0.08
    -powered
    0.08
    ä½ľä¸ºä¸Ģç§į
    0.08
    çĶ¨ä½ľ
    0.08
    ãĤĴ使ãģ£ãģŁ
    0.08
    çĶ¨äºİ
    0.08
    Activations Density 0.843%

    No Known Activations