© 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. 60517
    Prev
    Next
    INDEX
    Explanations

    just different

    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
    yet
    -0.09
    ä¸įä»ħä»ħ
    -0.08
    ä¸įä»ħéľĢè¦ģ
    -0.08
    Yet
    -0.08
    even
    -0.08
    —even
    -0.08
     EVEN
    -0.08
    éĺħ读åħ¨æĸĩ
    -0.08
    mil
    -0.08
     yet
    -0.07
    POSITIVE LOGITS
    èĢĮå·²
    0.19
    ç½¢äºĨ
    0.13
    ç½·
    0.11
     *}
    0.10
    è´µ
    0.09
     ë¿IJ
    0.09
    )}.
    0.09
    '}
    0.09
    ";}
    0.08
     thôi
    0.08
    Activations Density 0.184%

    No Known Activations