© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2421
    Prev
    Next
    INDEX
    Explanations

    business needs and solutions

    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
    rita
    -0.08
    niku
    -0.08
    -Mart
    -0.08
    atakan
    -0.08
    иÑģÑĤо
    -0.08
    Ī¬
    -0.08
    Lazy
    -0.07
    uston
    -0.07
    _packages
    -0.07
    第ä¸īåIJį
    -0.07
    POSITIVE LOGITS
    Âł
    0.09
    &
    0.07
    OS
    0.07
     –
    0.06
    of
    0.06
     today
    0.06
     increasingly
    0.06
    èĮ²
    0.06
    ä¸ĭéĿ¢å°ıç¼ĸ
    0.06
    ï¼Ĩ
    0.06
    Activations Density 2.360%

    No Known Activations