© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48255
    Prev
    Next
    INDEX
    Explanations

    calculation questions

    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
    Bags
    -0.08
    <[
    -0.08
    रण
    -0.08
    ymes
    -0.08
    sbin
    -0.07
    dfa
    -0.07
    ä¸įå°į
    -0.07
    alin
    -0.07
    åħ¬åŃIJ
    -0.07
    aldi
    -0.07
    POSITIVE LOGITS
    ä¸ĭåĪĹ
    0.07
    ä¸ĭåĪĹéĹ®é¢ĺ
    0.07
    ä¸ĭåĪĹ说æ³ķ
    0.07
    ä¸ĭåIJĮ
    0.07
    éĶĻ误çļĦæĺ¯
    0.07
    æľīåĵª
    0.06
     roast
    0.06
    è¯ķ
    0.06
    åĨħ容æľī
    0.06
    ÑıÑĢ
    0.06
    Activations Density 0.105%

    No Known Activations