© 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. 20229
    Prev
    Next
    INDEX
    Explanations

    writing, teaching, saying, or doing something

    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
    åĶ§
    -0.07
    uset
    -0.07
     bana
    -0.06
    æķĻèĤ²å·¥ä½ľ
    -0.06
    ="/"
    -0.06
    ç¢İçļĦ
    -0.06
     '\'
    -0.06
    æĸ¯é¡¿
    -0.06
    .TH
    -0.06
    èĢĮå½Ĵ
    -0.06
    POSITIVE LOGITS
    ç¾İå¾Ĺ
    0.08
    kurat
    0.07
    ç»ıèIJ¥ä¸»ä½ĵ
    0.07
     tráng
    0.07
    .trigger
    0.07
    ä¹ĭæĹ¥èµ·
    0.07
    heiro
    0.07
    emeld
    0.07
    asad
    0.07
    ฯ
    0.06
    Activations Density 0.010%

    No Known Activations