© 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. 47778
    Prev
    Next
    INDEX
    Explanations

    at/of

    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
    Âł
    -0.09
    -0.09
    ®
    -0.07
    tip
    -0.06
    /msg
    -0.06
    碧çİī
    -0.06
    urat
    -0.06
    èĭĽ
    -0.06
     Furthermore
    -0.06
    å¿Į
    -0.06
    POSITIVE LOGITS
     ^=
    0.08
    =-=-=-=-=-=-=-=-
    0.07
    ikut
    0.07
    оÑĢÑĤи
    0.07
     consc
    0.07
    egin
    0.07
    æľªåıĸå¾Ĺ
    0.07
    unky
    0.07
    ä¸ĢæľĿ
    0.07
    __:
    0.07
    Activations Density 0.001%

    No Known Activations