© 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. 38018
    Prev
    Next
    INDEX
    Explanations

    Rachel cook

    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
    eson
    -0.07
    æĺ¯èĩª
    -0.07
    æĩ
    -0.07
    erson
    -0.07
    gesetz
    -0.06
    _EXPORT
    -0.06
    est
    -0.06
    swer
    -0.06
    ae
    -0.06
    aa
    -0.06
    POSITIVE LOGITS
    è¿Ľä¸ĢæŃ¥äºĨ解
    0.07
    pute
    0.07
    _maker
    0.07
    è´¨éĩıçļĦ
    0.07
    è¿Ľä¸ĢæŃ¥åĬłå¤§
    0.07
    ingan
    0.07
     typename
    0.07
    isst
    0.07
    pell
    0.07
     nargs
    0.07
    Activations Density 0.008%

    No Known Activations