© 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. 19192
    Prev
    Next
    INDEX
    Explanations

    blackjack

    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
    itsu
    -0.08
    unik
    -0.08
    çīĻ
    -0.08
    idler
    -0.07
    å§Ĭ
    -0.07
     medically
    -0.07
    umn
    -0.07
    yim
    -0.07
    uso
    -0.07
    garan
    -0.07
    POSITIVE LOGITS
     Pars
    0.07
     cour
    0.06
    åħ³éŨ
    0.06
    è´¯
    0.06
     Cour
    0.06
    áºŃy
    0.06
     COUR
    0.06
    ones
    0.05
    Pg
    0.05
    own
    0.05
    Activations Density 0.669%

    No Known Activations