© 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. 10880
    Prev
    Next
    INDEX
    Explanations

    Solve for variable

    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
    ÑģÑĤила
    -0.06
    зов
    -0.06
    нок
    -0.06
    nok
    -0.06
     Full
    -0.06
    ower
    -0.06
    éªģ
    -0.06
    anel
    -0.06
     Spar
    -0.06
    èķĥ
    -0.05
    POSITIVE LOGITS
    teri
    0.08
    felder
    0.08
    ((&
    0.08
    upo
    0.08
    NameValuePair
    0.08
     запла
    0.07
    imore
    0.07
    缸è¾ħ缸æĪIJ
    0.07
    cassert
    0.07
    ียà¹Į
    0.07
    Activations Density 0.003%

    No Known Activations