© 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. 64957
    Prev
    Next
    INDEX
    Explanations

    accuracy and correctness

    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
    manda
    -0.07
    fra
    -0.07
    nell
    -0.07
    iena
    -0.06
    odge
    -0.06
    rene
    -0.06
    VALUES
    -0.06
    igits
    -0.06
    uel
    -0.06
    поле
    -0.06
    POSITIVE LOGITS
    åľ°è¯´
    0.09
    zcze
    0.09
    еÑģÑĤв
    0.08
    æııè¿°äºĨ
    0.08
    ook
    0.08
     bahwa
    0.08
    并èĮĤ
    0.08
    oden
    0.08
    æ¦Ĥæĭ¬
    0.08
    æııè¿°
    0.07
    Activations Density 0.006%

    No Known Activations