© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15184
    Prev
    Next
    INDEX
    Explanations

    code brackets and punctuation

    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
     puisqu
    -0.07
    ä¸ĥéĩĮ
    -0.06
    åĬłè½½æĽ´å¤ļ
    -0.06
    è¿Ľä¸ĢæŃ¥æıIJé«ĺ
    -0.06
    amment
    -0.06
     davantage
    -0.06
    æĹ¢çĦ¶
    -0.06
    ampa
    -0.06
    ãģ¾ãģ¾
    -0.06
    _cast
    -0.06
    POSITIVE LOGITS
    å¦Ĥæŀľæľī
    0.09
    onde
    0.08
    bote
    0.07
    μÏĢο
    0.07
    orter
    0.07
    èĭ¥æľī
    0.07
     thì
    0.07
    åĨħ容æĺ¯
    0.07
    å½ķçĶ¨
    0.07
    .ng
    0.07
    Activations Density 0.024%

    No Known Activations