© 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. 61010
    Prev
    Next
    INDEX
    Explanations

    writing and drawing instruments

    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
     buc
    -0.08
    _invoke
    -0.07
    antar
    -0.07
    ÑĢка
    -0.07
    çĴĭ
    -0.07
    欢声
    -0.07
     packaged
    -0.07
    æīĵåĮħ
    -0.06
     Ñģезон
    -0.06
    imers
    -0.06
    POSITIVE LOGITS
    纸ä¸Ĭ
    0.13
    ç¬Ķ
    0.12
     pencil
    0.12
     scri
    0.12
    éĵħç¬Ķ
    0.12
     каÑĢанда
    0.12
    çŃĨ
    0.12
    åŃĹ迹
    0.11
     ink
    0.11
    éĴ¢ç¬Ķ
    0.11
    Activations Density 0.122%

    No Known Activations