© 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. 41737
    Prev
    Next
    INDEX
    Explanations

    upright microscopes, suspension tests

    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
     rel
    -0.07
    åIJĪçIJĨåľ°
    -0.07
    re
    -0.07
    åħ¬æľī
    -0.07
     suite
    -0.07
    EEK
    -0.07
     koh
    -0.07
    suite
    -0.06
    继
    -0.06
    èĨĺ
    -0.06
    POSITIVE LOGITS
    izr
    0.08
     заÑģе
    0.08
    ortun
    0.08
     interiores
    0.08
    æĬ½è±¡
    0.08
    olim
    0.08
     intérieur
    0.08
    acol
    0.08
    onat
    0.08
    sert
    0.08
    Activations Density 0.784%

    No Known Activations