© 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. 51085
    Prev
    Next
    INDEX
    Explanations

    affinity constants or coefficients

    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
    inz
    -0.08
    æĥĬå¿ĥ
    -0.08
    ElementException
    -0.07
    สะà¸Ķ
    -0.07
    asic
    -0.07
    /sn
    -0.07
    üre
    -0.07
     outs
    -0.07
    -ves
    -0.07
     ì§Ģìłģ
    -0.07
    POSITIVE LOGITS
    abi
    0.07
    akai
    0.07
     favour
    0.07
    erner
    0.07
     favourable
    0.07
     favorable
    0.07
    ju
    0.07
    æľĹ
    0.06
     governing
    0.06
     favor
    0.06
    Activations Density 0.001%

    No Known Activations