© 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. 13497
    Prev
    Next
    INDEX
    Explanations

    people's names followed by actions

    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
    家天ä¸ĭ
    -0.08
    åŃĺæľī
    -0.07
    Ĩµ
    -0.07
    obl
    -0.07
    å°±åı«
    -0.06
     Isl
    -0.06
    èµļäºĨ
    -0.06
    udar
    -0.06
    estal
    -0.06
    ypes
    -0.06
    POSITIVE LOGITS
    çĶ«
    0.08
    leman
    0.07
    åĩĨç¡®æĬĬæı¡
    0.07
    æıIJåĩºçļĦéĹ®é¢ĺ
    0.07
    igi
    0.07
    åĬŁåºķ
    0.07
    ÏĨαν
    0.07
    ¤í
    0.07
    pond
    0.07
    idane
    0.06
    Activations Density 0.001%

    No Known Activations