© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 7656
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
    adelphia
    -0.07
    ниÑĨÑĮ
    -0.07
    ảy
    -0.07
    .TryParse
    -0.06
    illos
    -0.06
    ollywood
    -0.06
    æĬ
    -0.06
    ány
    -0.06
    .rpm
    -0.06
    ýt
    -0.06
    POSITIVE LOGITS
    oen
    0.07
    Ĥ¹
    0.07
    è§£éĩĬ说
    0.07
    ç¾İä¸įèĥľæĶ¶
    0.07
    æľĢåIJİä¸Ģ天
    0.07
     funktion
    0.07
    REE
    0.07
     meanwhile
    0.07
    nth
    0.07
    éªĦéĺ³
    0.07
    Activations Density 0.013%

    No Known Activations