© 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. 3303
    Prev
    Next
    INDEX
    Explanations

    starch and potato

    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
    åĨ½
    -0.08
    trash
    -0.07
    ittel
    -0.07
    заÑħ
    -0.07
    oms
    -0.07
    æĺ¥èī²
    -0.07
    ibri
    -0.07
    iqu
    -0.07
    lass
    -0.07
    ighth
    -0.06
    POSITIVE LOGITS
    flation
    0.08
    itect
    0.08
    èĨ¨
    0.08
    orsz
    0.08
     starch
    0.07
    ardy
    0.07
    estä
    0.07
    abh
    0.07
    igl
    0.07
     ê´´
    0.07
    Activations Density 0.022%

    No Known Activations