© 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. 33279
    Prev
    Next
    INDEX
    Explanations

    probability, fee, probability

    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
    建平
    -0.08
    大年
    -0.08
    fatt
    -0.07
    _resize
    -0.07
    æ°¯ä¹Ļçĥ¯
    -0.07
    arian
    -0.07
    _BINARY
    -0.07
    æĿĢæİī
    -0.07
    owan
    -0.07
    fires
    -0.07
    POSITIVE LOGITS
    æłĩ
    0.07
    ردÙĩ
    0.07
     accurately
    0.07
    éĩįè¦ģæĮĩ示
    0.06
    åĵģ
    0.06
     correctly
    0.06
    çķĻä¸ĭä¸Ģ
    0.06
    åħļé£İå»īæĶ¿å»ºè®¾åĴĮ
    0.06
    éŨå¤ĸ
    0.06
    æĺİæľĪ
    0.06
    Activations Density 0.013%

    No Known Activations