© 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. 3015
    Prev
    Next
    INDEX
    Explanations

    `č` before `$ USAGE` or code examples

    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
    å°Ķå¤ļ
    -0.07
    Ìģ
    -0.06
    [^
    -0.06
    -0.06
    ,
    -0.06
    ģ
    -0.06
     Lalu
    -0.06
    aná
    -0.06
    ä¸Ńè¿ĺ
    -0.06
    空头
    -0.06
    POSITIVE LOGITS
    jenigen
    0.08
    ÙĨÙĩ
    0.08
    lick
    0.08
    ни
    0.08
    ziger
    0.08
    er
    0.08
    ÙĦØ©
    0.08
    ÙĨ
    0.08
    impin
    0.08
    ly
    0.08
    Activations Density 0.237%

    No Known Activations