© 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. 50944
    Prev
    Next
    INDEX
    Explanations

    undergo conversion, proliferation, oxidative changes

    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
    /english
    -0.08
    èµ·è§ģ
    -0.08
    ruz
    -0.07
    举åİ¿
    -0.07
    mong
    -0.07
    ìį¨
    -0.07
    -hand
    -0.07
    /ns
    -0.07
    not
    -0.07
    zcze
    -0.07
    POSITIVE LOGITS
    es
    0.10
    ered
    0.09
    ä¸Ģç³»åĪĹçļĦ
    0.09
    ãģ¹ãģį
    0.08
    ä¸Ģç³»åĪĹ
    0.08
    ä½Ĩä¸įéĻIJäºİ
    0.08
    æĹ¥æĹ©ä¸Ĭ
    0.08
    ering
    0.07
    esimo
    0.07
    ivable
    0.07
    Activations Density 0.022%

    No Known Activations