© 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. 45966
    Prev
    Next
    INDEX
    Explanations

    difference between

    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
    ä½ķç§į
    -0.12
     jedoch
    -0.12
     ÙĨÛĮز
    -0.12
    åį³ä¸º
    -0.11
    å¹¶æľª
    -0.10
    并éĿŀæĺ¯
    -0.10
    è¾ĥ为
    -0.09
    å°ĨæѤ
    -0.09
    ä¹Łæĺ¯åįģåĪĨ
    -0.09
    ä»ħéľĢ
    -0.09
    POSITIVE LOGITS
    æľī个
    0.11
    没æ³ķ
    0.11
     gotta
    0.10
     поÑĤом
    0.10
    åĨįæĬĬ
    0.10
    åħĪæĬĬ
    0.10
    è¿ĺæľī个
    0.10
    ä¸ĢåłĨ
    0.10
     really
    0.10
     basically
    0.10
    Activations Density 0.033%

    No Known Activations