© 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. 9812
    Prev
    Next
    INDEX
    Explanations

    possessive determiner + noun/adjective

    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
    ivière
    -0.10
    éĩįè¦ģçļĦäºĭæĥħ
    -0.09
    ahas
    -0.09
    odon
    -0.08
    åĬ¨åĬĽæĸ¹éĿ¢
    -0.08
    黯
    -0.08
    öd
    -0.08
    æĿİè½»
    -0.08
    áĥ®
    -0.08
    ansch
    -0.08
    POSITIVE LOGITS
     own
    0.14
    own
    0.11
    èĩªèº«
    0.09
    èĩªèº«çļĦ
    0.08
    à¹Ģà¸Ńà¸ĩ
    0.08
    /
    0.08
     Own
    0.07
    èĩªå·±çļĦ
    0.07
     vs
    0.07
    V
    0.07
    Activations Density 0.419%

    No Known Activations