© 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. 60401
    Prev
    Next
    INDEX
    Explanations

    array data types

    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
    riu
    -0.07
    è²Į
    -0.07
    arn
    -0.06
     finally
    -0.06
    éĩĬæĶ¾
    -0.06
    avor
    -0.06
    orm
    -0.06
    èĩªåľ¨
    -0.06
    orsi
    -0.06
    è±ģ
    -0.06
    POSITIVE LOGITS
    ennen
    0.08
    ghest
    0.08
    笳
    0.08
    ä»Ĭ年以æĿ¥
    0.07
    äºİä»Ĭå¹´
    0.07
    åįĥ家
    0.07
    _launch
    0.07
    баÑĤ
    0.07
    اج
    0.07
    andie
    0.07
    Activations Density 0.005%

    No Known Activations