© 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. 57621
    Prev
    Next
    INDEX
    Explanations

    headed by Eleanor or Bill

    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
    æĿİ家
    -0.08
    presse
    -0.08
    å¤ıæ´Ľ
    -0.08
     Huckabee
    -0.08
    éķ¿çŁŃ
    -0.07
    haps
    -0.07
    usul
    -0.07
     Bakal
    -0.07
    çĪ±ä¸½ä¸Ŀ
    -0.07
     Biá»ĩt
    -0.07
    POSITIVE LOGITS
     K
    0.07
    åľ¨ä¸ĸ
    0.07
    èijĹåIJį
    0.07
     Christian
    0.07
     anonymous
    0.07
     fr
    0.06
     C
    0.06
     DJ
    0.06
     Al
    0.06
     J
    0.06
    Activations Density 1.932%

    No Known Activations