© 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. 26132
    Prev
    Next
    INDEX
    Explanations

    if and only if

    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
    cyj
    -0.08
    è¿ĺ以为
    -0.08
    为åķ¥
    -0.07
    æĥ³çľĭ
    -0.07
    itati
    -0.07
    åħ³æ³¨æĪij们
    -0.07
    uez
    -0.07
     certainement
    -0.07
    æĤ¨åı¯èĥ½
    -0.07
    ä¸įåı¯åIJ¦è®¤
    -0.07
    POSITIVE LOGITS
    èĥ½å¤Łåľ¨
    0.08
    èĥ½å¤ŁéĢļè¿ĩ
    0.08
    æľīè¶³å¤ŁçļĦ
    0.08
     somehow
    0.08
    èĥ½åľ¨
    0.07
     (!((
    0.07
    没æľīåľ¨
    0.07
    èĩ³å°ijæľī
    0.07
    以ä¸ĭæĿ¡ä»¶
    0.07
     almeno
    0.07
    Activations Density 0.023%

    No Known Activations