© 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. 46834
    Prev
    Next
    INDEX
    Explanations

    initiate or sickness

    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
    USR
    -0.07
    è¡«
    -0.06
    ibal
    -0.06
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.06
    )":
    -0.06
    -packages
    -0.06
    allery
    -0.06
    THR
    -0.06
     odnosno
    -0.06
    /www
    -0.06
    POSITIVE LOGITS
    ãĢįãĢģ
    0.12
    ãģłãģĹ
    0.11
    并ä¸Ķåľ¨
    0.11
    ãģ§ãģĻãģĹ
    0.10
    ï¼īãĢģ
    0.10
    ãĢįãĢģãĢĮ
    0.10
    并ä¸Ķ
    0.10
     ìķĦëĭĪë©°
    0.10
    èĢĮä¸Ķåľ¨
    0.10
    )ãĢģ
    0.10
    Activations Density 0.337%

    No Known Activations