© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15209
    Prev
    Next
    INDEX
    Explanations

    succinate formation

    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
    igon
    -0.08
    åĢĴ
    -0.08
    ungsver
    -0.07
    ersp
    -0.07
    缺ä¸Ģ
    -0.07
    æĸĮ
    -0.07
    ÑĢоÑģ
    -0.07
    .Usage
    -0.07
    ç½Ĺ纳
    -0.07
    樹
    -0.07
    POSITIVE LOGITS
    oubl
    0.07
    æĽ²åŃIJ
    0.07
     Caught
    0.07
    ye
    0.07
    èı¸
    0.07
    assign
    0.07
    ehu
    0.07
    caught
    0.07
    oller
    0.07
    ycin
    0.07
    Activations Density 0.001%

    No Known Activations