© 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. 47086
    Prev
    Next
    INDEX
    Explanations

    ranges, quantities, or dimensions

    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
    æµģè¨Ģ
    -0.08
    ä¸Ģå®ļ
    -0.08
    æīĢæľīçļĦ人
    -0.08
    ä¸įåİĮ
    -0.08
    ONUS
    -0.07
    äºĨä¸Ģå®ļ
    -0.07
    ubi
    -0.07
     wahrscheinlich
    -0.07
    SEQ
    -0.07
    æĺ¯åħ¨
    -0.07
    POSITIVE LOGITS
    åĬ¨è¾Ħ
    0.13
     typically
    0.12
     ranging
    0.12
     typical
    0.11
     ranges
    0.11
    ä¸ĢèĪ¬ä¸º
    0.11
    ä¸ĢèĪ¬åľ¨
    0.10
    éĢļå¸¸åľ¨
    0.10
    大å¤ļæĺ¯
    0.10
    ä¸ĢèĪ¬éĥ½
    0.10
    Activations Density 0.101%

    No Known Activations