© 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. 41916
    Prev
    Next
    INDEX
    Explanations

    audience identification

    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
    oola
    -0.08
    ichel
    -0.08
    묵
    -0.08
    å·¥ç¨ĭå¸ĪæĭĽèģĺ
    -0.08
    zeh
    -0.08
    ç»ıçIJĨæĭĽèģĺ
    -0.07
     incond
    -0.07
    داب
    -0.07
    çĥŃéŨæłĩçŃ¾
    -0.07
    æĬĬ头
    -0.07
    POSITIVE LOGITS
     likely
    0.09
    å¾Īåı¯èĥ½æĺ¯
    0.09
    å¾Īæľīåı¯èĥ½
    0.08
    å¾Īåı¯èĥ½
    0.08
    æľīåı¯èĥ½æĺ¯
    0.08
    ighth
    0.08
    çļĦåı¯èĥ½
    0.07
     unlikely
    0.07
     probably
    0.07
     probable
    0.07
    Activations Density 0.021%

    No Known Activations