© 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. 18962
    Prev
    Next
    INDEX
    Explanations

    indexed elements

    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
    ub
    -0.08
    idge
    -0.07
    acken
    -0.07
    ::$
    -0.07
    onet
    -0.07
    Dismiss
    -0.07
    ลัà¸ļ
    -0.06
     Niest
    -0.06
    æī«ä¸Ģæī«
    -0.06
    icto
    -0.06
    POSITIVE LOGITS
     indeed
    0.08
     fifth
    0.07
    ç¡®å®ŀ
    0.07
    erei
    0.07
    aget
    0.07
     seventh
    0.07
     eighth
    0.07
    woo
    0.07
    ergen
    0.07
     sixth
    0.07
    Activations Density 0.001%

    No Known Activations