© 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. 64505
    Prev
    Next
    INDEX
    Explanations

    if ... then

    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
     probably
    -0.10
    ];
    -0.09
    ï¼Ľ
    -0.09
     Probably
    -0.08
     ;
    -0.08
    probably
    -0.08
    ;
    -0.08
    %;
    -0.08
    *;
    -0.07
    åºĶæĺ¯
    -0.07
    POSITIVE LOGITS
     dovesse
    0.12
    )))),
    0.12
     somehow
    0.11
    ))),
    0.11
    æľīä»»ä½ķ
    0.11
    è¿Ļæł·çļĦè¯Ŀ
    0.11
     fosse
    0.10
     fossero
    0.10
     fizer
    0.10
    æŀľçľŁ
    0.10
    Activations Density 0.213%

    No Known Activations