© 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. 62902
    Prev
    Next
    INDEX
    Explanations

    possessive endings 's

    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
    COMMENT
    -0.08
    onde
    -0.08
    注æĦıåĪ°
    -0.07
    undler
    -0.07
    _validator
    -0.07
    VOKE
    -0.07
    å¯Ħæīĺ
    -0.07
    epen
    -0.07
    lesi
    -0.07
    sez
    -0.07
    POSITIVE LOGITS
    ppt
    0.10
     PowerPoint
    0.09
     ppt
    0.09
     presentations
    0.09
    å¹»çģ¯çīĩ
    0.08
     slides
    0.08
     presentation
    0.08
    resentation
    0.08
    课件
    0.08
     slide
    0.08
    Activations Density 0.025%

    No Known Activations