© 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. 57709
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms

    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
    hill
    -0.08
    locker
    -0.07
    lix
    -0.07
    hip
    -0.07
    hips
    -0.07
    æĹłæķĪ
    -0.07
    orry
    -0.07
    kee
    -0.07
    éĺ²çĪĨ
    -0.06
    å°±æĢķ
    -0.06
    POSITIVE LOGITS
    硬çļĦ
    0.07
    审
    0.07
     измеÑĢÑı
    0.07
    大ä¸Ń
    0.07
     ìĦŃ
    0.06
     Pey
    0.06
    骨头
    0.06
    lef
    0.06
    æĿijä¸Ĭ
    0.06
    _hooks
    0.06
    Activations Density 0.011%

    No Known Activations