© 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. 38133
    Prev
    Next
    INDEX
    Explanations

    reviewed, regarding, reply, noted

    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
     somewhere
    -0.07
    ANTE
    -0.06
    åį´ä¸įçŁ¥éģĵ
    -0.06
    à¦Łà§ĩ
    -0.06
    ä»ĸ们åı¯ä»¥
    -0.06
     someday
    -0.06
    ä»ĸ们è¿ĺ
    -0.06
     nearest
    -0.06
    ame
    -0.06
     camel
    -0.06
    POSITIVE LOGITS
    rov
    0.09
    é«ĺå¯Ĩ
    0.09
    代çIJĨæľīéĻIJåħ¬åı¸
    0.08
    ree
    0.08
    è§Ī
    0.08
    \Factory
    0.08
     Reviewed
    0.08
    æĪij社
    0.07
    umba
    0.07
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    0.07
    Activations Density 0.008%

    No Known Activations