© 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. 34220
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and religious figures

    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
    elang
    -0.07
    åħ·æľīä¸Ģå®ļçļĦ
    -0.06
    еÑħ
    -0.06
    åıĹçĽĬ
    -0.06
    è´¡
    -0.06
    _UNIX
    -0.06
    æľįçĶ¨
    -0.06
     homen
    -0.06
    åIJį家
    -0.06
     aprox
    -0.06
    POSITIVE LOGITS
     Himself
    0.14
    ç¥Ĥ
    0.13
     سبØŃاÙĨÙĩ
    0.12
    èµIJäºĪ
    0.11
    èµIJ
    0.10
     Almighty
    0.10
    èĢģ人家
    0.09
    è³ľ
    0.09
     omnip
    0.09
     تعاÙĦÙī
    0.08
    Activations Density 0.078%

    No Known Activations