© 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. 9896
    Prev
    Next
    INDEX
    Explanations

    limit expressions

    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
    sey
    -0.08
    以å¤ĸçļĦ
    -0.08
    stadt
    -0.07
    vel
    -0.07
    ito
    -0.07
    .INSTANCE
    -0.07
    ette
    -0.07
    jenigen
    -0.07
    ware
    -0.07
    /or
    -0.06
    POSITIVE LOGITS
    gether
    0.10
    æĢ§åľ°
    0.08
    踵
    0.08
    warzys
    0.08
    elop
    0.08
    ï¸İ
    0.08
    oward
    0.07
    ä½ķæĸ¹
    0.07
    ä¸Ĭä¹Ł
    0.07
    ypes
    0.07
    Activations Density 0.002%

    No Known Activations