© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21937
    Prev
    Next
    INDEX
    Explanations

    trademark symbols

    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
    iet
    -0.06
    u
    -0.06
    ois
    -0.06
    ic
    -0.06
    bi
    -0.06
    ocal
    -0.06
    ouis
    -0.06
    ing
    -0.06
    Ac
    -0.06
     Corps
    -0.06
    POSITIVE LOGITS
    æ³ĵ
    0.09
    ysh
    0.08
    onel
    0.08
    PageIndex
    0.08
    onnée
    0.08
    ornings
    0.07
    avery
    0.07
    ásticas
    0.07
    waren
    0.07
    zych
    0.07
    Activations Density 0.364%

    No Known Activations