© 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. 13624
    Prev
    Next
    INDEX
    Explanations

    convergence or count of n

    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
    æĥŁæľī
    -0.07
    azz
    -0.07
    pil
    -0.07
    ä¸Ģåĩ»
    -0.07
    aren
    -0.07
     Weih
    -0.07
    aget
    -0.06
    κÏģα
    -0.06
    Context
    -0.06
    [:-
    -0.06
    POSITIVE LOGITS
     Counts
    0.07
    hä
    0.07
     counts
    0.07
     annivers
    0.07
    hana
    0.07
     count
    0.07
    akov
    0.07
    bury
    0.07
     Count
    0.06
     ngẫu
    0.06
    Activations Density 0.003%

    No Known Activations