© 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. 24022
    Prev
    Next
    INDEX
    Explanations

    low/high rates

    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
    EXPR
    -0.09
    æĽ´éĩįè¦ģçļĦ
    -0.09
    åħ¨éĥ¨éĥ½æĺ¯
    -0.08
    æĹłæķĪçļĦ
    -0.08
    顾åIJįæĢĿ
    -0.08
    ä¸įåģľçļĦ
    -0.08
    éĶ¦æ¶Ľ
    -0.08
    太大äºĨ
    -0.08
    太å¤ļçļĦ
    -0.08
    ä¸Ģ模
    -0.08
    POSITIVE LOGITS
    è¿ľ
    0.07
    aea
    0.07
    è¼ĥ
    0.07
    åıĬ使çĶ¨
    0.07
    aths
    0.07
    çĶļ
    0.06
    æľīéĻIJ
    0.06
    å°
    0.06
    è¾ĥ
    0.06
    åĴĮ使çĶ¨
    0.06
    Activations Density 0.036%

    No Known Activations