© 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. 24630
    Prev
    Next
    INDEX
    Explanations

    numbers and amounts

    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
    ulli
    -0.09
    ndon
    -0.08
    illac
    -0.08
    æīijéĿ¢
    -0.08
    壮大çļĦ
    -0.08
    strup
    -0.08
    ä¸įåĩı
    -0.08
    éĹŃåħ³
    -0.08
    åģıå¼±
    -0.08
    iglio
    -0.08
    POSITIVE LOGITS
     lap
    0.06
     Fleming
    0.06
    女æľĭåıĭ
    0.06
    ped
    0.06
     Son
    0.06
    l
    0.06
    plot
    0.06
    æŁIJ
    0.05
    see
    0.05
    ought
    0.05
    Activations Density 0.022%

    No Known Activations