© 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. 11318
    Prev
    Next
    INDEX
    Explanations

    suggesting new findings

    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
    ноÑģÑĤÑıми
    -0.07
    æ¯
    -0.06
    订
    -0.06
    ستر
    -0.06
    åĢ¼å¾Ĺä¸Ģ
    -0.06
    ÃŃna
    -0.06
    }\"
    -0.06
    对åºĶçļĦ
    -0.06
    çŁ¥éģĵ
    -0.06
    å¹³éĿĻ
    -0.06
    POSITIVE LOGITS
    yek
    0.08
    æĽ´ç²¾å½©
    0.07
    jam
    0.07
    plays
    0.07
    åħŃçĤ¹
    0.07
    igy
    0.07
    æ¯Ķäºļ
    0.07
    igs
    0.07
    rank
    0.07
    åĸľæ¬¢åIJĥ
    0.07
    Activations Density 0.001%

    No Known Activations