© 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. 8766
    Prev
    Next
    INDEX
    Explanations

    doi:

    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
    egram
    -0.08
     presunto
    -0.08
    zada
    -0.07
    благо
    -0.07
    ascript
    -0.07
     Cib
    -0.07
    çī¹æľĹ
    -0.07
    κι
    -0.07
    asics
    -0.07
    inction
    -0.07
    POSITIVE LOGITS
    ä¹İ
    0.07
    åıİ
    0.07
    arkan
    0.07
    ãģĭãģĽ
    0.07
    ืà¹Īà¸Ń
    0.07
    ij¸
    0.07
     iler
    0.07
    á»±c
    0.07
    Pk
    0.07
    rus
    0.06
    Activations Density 0.003%

    No Known Activations