© 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. 24280
    Prev
    Next
    INDEX
    Explanations

    data dictionary

    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
    _RT
    -0.07
    çĶ¨äºº
    -0.07
     пом
    -0.07
    _cp
    -0.06
    çļĦå®īåħ¨
    -0.06
    å¸
    -0.06
    EP
    -0.06
    pom
    -0.06
    -&
    -0.06
    ono
    -0.06
    POSITIVE LOGITS
    rawer
    0.08
    åľĨ梦
    0.08
    çĮľä½łåĸľæ¬¢
    0.08
    agina
    0.08
    é¾ĻèĻİ
    0.08
    æľĢåIJİä¸Ģ页
    0.08
    regor
    0.08
    dain
    0.08
    梦ä¸Ń
    0.08
    ÐŁÐ¡
    0.08
    Activations Density 0.215%

    No Known Activations