© 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. 27334
    Prev
    Next
    INDEX
    Explanations

    number formats and Lock

    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
    æĿŀ
    -0.09
     Cooke
    -0.07
    IGIN
    -0.07
    REEN
    -0.07
    Courier
    -0.07
    iski
    -0.07
    峡
    -0.07
     —————————
    -0.07
    à¹ģรà¸ģà¸Ĺีà¹Ī
    -0.07
    -cookie
    -0.07
    POSITIVE LOGITS
    ждение
    0.06
    å®ĺæĸ¹å¾®ä¿¡
    0.06
    жда
    0.06
    ä¸Ģç«ł
    0.06
    ÑĤÑĢÑĥ
    0.06
     chapter
    0.06
    üd
    0.06
    /contact
    0.06
    amide
    0.06
    kod
    0.06
    Activations Density 0.016%

    No Known Activations