© 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. 27077
    Prev
    Next
    INDEX
    Explanations

    front end

    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
    atera
    -0.09
    keit
    -0.09
    gefü
    -0.08
    keiten
    -0.08
    à¹īย
    -0.08
    oftware
    -0.08
    ATER
    -0.08
    waran
    -0.08
    หมาย
    -0.08
    िता
    -0.08
    POSITIVE LOGITS
    -facing
    0.10
    /back
    0.09
    age
    0.09
    ed
    0.08
    eira
    0.08
    ivity
    0.08
    orial
    0.08
    iers
    0.08
    eced
    0.08
    alia
    0.08
    Activations Density 0.027%

    No Known Activations