© 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. 47609
    Prev
    Next
    INDEX
    Explanations

    HTML/web keywords

    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
    åŃ¦æľŁ
    -0.08
    磼
    -0.07
    neck
    -0.07
    .mb
    -0.06
    .getRuntime
    -0.06
    allis
    -0.06
    ams
    -0.06
    磩
    -0.06
    mb
    -0.06
    amb
    -0.06
    POSITIVE LOGITS
     $($
    0.08
    eut
    0.07
    elah
    0.07
     prestito
    0.07
    Blake
    0.07
    élo
    0.07
    WithString
    0.07
    éĢĤçĶ¨çļĦ
    0.07
    egger
    0.07
    erah
    0.07
    Activations Density 0.001%

    No Known Activations