© 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. 43573
    Prev
    Next
    INDEX
    Explanations

    my eyes vs. them

    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
    avel
    -0.08
    åIJĦæī§
    -0.07
    sterreich
    -0.07
    åĩºè´¨
    -0.07
    icola
    -0.07
    ydd
    -0.07
    rete
    -0.07
    å½ĵæĪij们
    -0.07
    æĪijä»¬åľ¨
    -0.07
     WITHOUT
    -0.07
    POSITIVE LOGITS
    çľĭæĿ¥
    0.10
    çľ¼ä¸Ń
    0.09
    çľ¼éĩĮ
    0.08
    çľ¼ä¸ŃçļĦ
    0.08
    ç¬Ķä¸ĭ
    0.07
    æĿ¥è¯´æĺ¯
    0.07
    å¿ĥ缮ä¸ŃçļĦ
    0.07
    å¿ĥ缮ä¸Ń
    0.07
     personally
    0.07
    çľĭä¾Ĩ
    0.07
    Activations Density 0.180%

    No Known Activations