© 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. 40836
    Prev
    Next
    INDEX
    Explanations

    normal vector

    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
    اÛĮØ´
    -0.07
    ä¹ĭæķ°
    -0.07
    æĢ»éĩıçļĦ
    -0.07
    tape
    -0.07
    è¿Ļ座åŁİå¸Ĥ
    -0.07
    .Transactional
    -0.07
    erma
    -0.07
     Individual
    -0.07
     bens
    -0.07
    .mapbox
    -0.07
    POSITIVE LOGITS
    vecs
    0.09
     vectors
    0.08
    çŁ¢
    0.08
    Resolved
    0.08
    çļĦæĸ¹åIJij
    0.08
    æĸ¹åIJij
    0.08
    -vector
    0.08
    Vector
    0.08
    çŁ¢éĩı
    0.08
    çī¹å°Ķ
    0.07
    Activations Density 0.004%

    No Known Activations