© 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. 15286
    Prev
    Next
    INDEX
    Explanations

    HourAhead hour

    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
    èĶĵ
    -0.07
    ει
    -0.07
    Æ¡i
    -0.07
    æľ½
    -0.07
    -bind
    -0.07
    夫æĸ¯åŁº
    -0.07
    æĿIJ
    -0.06
    avers
    -0.06
    çĮĽçĦ¶
    -0.06
    ப
    -0.06
    POSITIVE LOGITS
    æĪĺçļĦ
    0.07
     STDERR
    0.07
    ue
    0.07
    íĨ±
    0.07
    _plural
    0.07
    èĩªä¿¡çļĦ
    0.07
    ault
    0.06
    Parsed
    0.06
    ÈĽilor
    0.06
    Îĸ
    0.06
    Activations Density 0.058%

    No Known Activations