© 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. 3126
    Prev
    Next
    INDEX
    Explanations

    as high as, up to

    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
     likely
    -0.08
    大æ¦Ĥæĺ¯
    -0.08
    åĽłæĤ¨çļĦ
    -0.08
    ĵ¨
    -0.08
    大èĩ´
    -0.08
    大æ¦Ĥ
    -0.08
    likely
    -0.08
    å¼ķãģįç¶ļãģį
    -0.07
    zyd
    -0.07
    æŃ£å¥½
    -0.07
    POSITIVE LOGITS
    çĶļèĩ³
    0.16
    çĶļèĩ³åı¯ä»¥
    0.14
    çĶļèĩ³æĺ¯
    0.13
    å¤ļè¾¾
    0.13
    çĶļèĩ³åľ¨
    0.13
    çĶļèĩ³ä¼ļ
    0.13
    çĶļèĩ³æľī
    0.12
    çĶļèĩ³äºİ
    0.12
     even
    0.12
     ìĭ¬ì§Ģìĸ´
    0.12
    Activations Density 0.237%

    No Known Activations