© 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. 60930
    Prev
    Next
    INDEX
    Explanations

    citations or scientific publications

    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
     Staats
    -0.06
    æĤ¬
    -0.06
     Top
    -0.06
    注éĩį
    -0.06
     supr
    -0.06
     Heim
    -0.06
    alg
    -0.06
    éģ¿è®©
    -0.06
    eous
    -0.06
    estead
    -0.06
    POSITIVE LOGITS
    utin
    0.08
    Dup
    0.08
    waran
    0.08
    UDI
    0.08
    _unset
    0.08
    aroo
    0.07
    ngu
    0.07
    ìŀ¡
    0.07
    _war
    0.07
    .tem
    0.07
    Activations Density 0.014%

    No Known Activations