© 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. 43655
    Prev
    Next
    INDEX
    Explanations

    off-topic or off-road

    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
    ekyll
    -0.09
    ìļ±
    -0.09
    à¹Ģà¸Ķียวà¸ģัà¸ļ
    -0.08
    mares
    -0.08
    othing
    -0.08
    ameran
    -0.08
    chtig
    -0.08
    queira
    -0.07
    werkt
    -0.07
    mehr
    -0.07
    POSITIVE LOGITS
     khá»ıi
    0.10
    ensively
    0.09
     hẳn
    0.09
    ÑģÑİда
    0.08
    imate
    0.08
    entimes
    0.08
    ç´§è¦ģ
    0.08
    æ¦Ľ
    0.07
    ¯
    0.07
    ensive
    0.07
    Activations Density 0.094%

    No Known Activations