© 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. 62217
    Prev
    Next
    INDEX
    Explanations

    completion of a task

    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
    dorf
    -0.10
    remen
    -0.10
    ï¸İ
    -0.09
    onnier
    -0.09
    nyder
    -0.09
    texte
    -0.08
    wai
    -0.08
    den
    -0.08
    rett
    -0.08
    maÃŁ
    -0.08
    POSITIVE LOGITS
    wards
    0.09
    åĻľ
    0.07
    emos
    0.07
    kort
    0.07
    herent
    0.07
    ement
    0.07
    heits
    0.07
    оÑĢод
    0.07
    ertz
    0.06
    esch
    0.06
    Activations Density 0.037%

    No Known Activations