© 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. 64069
    Prev
    Next
    INDEX
    Explanations

    synaptonemal complexes or oogenesis

    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
    fty
    -0.07
    metro
    -0.07
    [::-
    -0.07
    dash
    -0.07
    æĹłå¾®ä¸įèĩ³
    -0.06
    ramids
    -0.06
    ãĥ©ãĥ«
    -0.06
    Dash
    -0.06
     dash
    -0.06
    趣
    -0.06
    POSITIVE LOGITS
    angan
    0.08
     outcomes
    0.07
    uide
    0.07
    æł¹éĥ¨
    0.07
     propagate
    0.07
    Completion
    0.07
    -wide
    0.07
    ëıĪ
    0.07
     propagation
    0.06
     Jacqu
    0.06
    Activations Density 0.011%

    No Known Activations