© 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. 27870
    Prev
    Next
    INDEX
    Explanations

    English words and punctuation

    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
    '&&
    -0.07
    大èĥĨçļĦ
    -0.07
    bag
    -0.07
     Corr
    -0.07
    æĿĥå¨ģçļĦ
    -0.07
    iele
    -0.06
     happening
    -0.06
    èĩ³å°ij
    -0.06
    uges
    -0.06
    å¾Īåı¯èĥ½
    -0.06
    POSITIVE LOGITS
    ä¸įè¿ĩè¿Ļ
    0.09
    ä½Ĩè¿Ļ
    0.08
    æ·ĩ
    0.08
    æľªæŀľ
    0.08
    ä½ĨéĢĻ
    0.07
    ä¸įè¿ĩ
    0.07
    ä¼ļæĽ´å¥½
    0.07
    вин
    0.07
    ä¸įè¿ĩåľ¨
    0.07
    ä½ĨéĤ£
    0.07
    Activations Density 0.013%

    No Known Activations