© 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. 17648
    Prev
    Next
    INDEX
    Explanations

    FILE extension

    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
    enga
    -0.07
    pcs
    -0.07
    orman
    -0.06
    धा
    -0.06
    ç¨
    -0.06
    ä¸Ģè§ģ
    -0.06
    躬
    -0.06
    Ầ
    -0.06
    pj
    -0.06
    çİīå±±
    -0.06
    POSITIVE LOGITS
    庶
    0.08
    -lnd
    0.07
    ioned
    0.07
    lobber
    0.07
    £¼
    0.06
    ĵ¨
    0.06
    нов
    0.06
    ÑĥеÑĤ
    0.06
    anded
    0.06
    witter
    0.06
    Activations Density 0.191%

    No Known Activations