© 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. 46865
    Prev
    Next
    INDEX
    Explanations

    asset related terms

    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
    zelf
    -0.09
    oriously
    -0.09
    er
    -0.08
    ãĥ£
    -0.08
    eries
    -0.08
    eworthy
    -0.07
    onese
    -0.07
    /she
    -0.07
    odos
    -0.07
    aptcha
    -0.07
    POSITIVE LOGITS
    umed
    0.09
    éĺ¶çº§çļĦ
    0.08
    chaft
    0.08
    ÙĪرÙĬ
    0.08
    ieke
    0.08
    inine
    0.08
     xá
    0.07
    ocracy
    0.07
    满满
    0.07
    uming
    0.07
    Activations Density 0.010%

    No Known Activations