© 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. 17362
    Prev
    Next
    INDEX
    Explanations

    array declarations with nested lists

    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
     ка
    -0.08
    è¡·
    -0.07
    à¯Ĩ
    -0.06
    åĨįçľĭçľĭ
    -0.06
    仲
    -0.06
    iasi
    -0.06
    il
    -0.06
    iru
    -0.06
    ª
    -0.06
    (a
    -0.06
    POSITIVE LOGITS
    ymo
    0.08
    мп
    0.07
    sor
    0.07
    ạt
    0.07
     Howard
    0.07
    çĸ¯äºĨ
    0.07
    zk
    0.07
    æıIJè¦ģ
    0.07
    اÙģع
    0.07
     selber
    0.07
    Activations Density 0.001%

    No Known Activations