© 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. 46016
    Prev
    Next
    INDEX
    Explanations

    reports, condition, produce, employment, activity

    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
    ima
    -0.06
    fert
    -0.06
    -0.06
    大èĩ´
    -0.06
    amica
    -0.05
    acea
    -0.05
     forcibly
    -0.05
    hips
    -0.05
    -0.05
    istan
    -0.05
    POSITIVE LOGITS
    sic
    0.09
    ë¦Ħ
    0.08
    ä¾¥
    0.08
    FileNotFoundException
    0.08
    izr
    0.08
    ãĤĵãģ³
    0.08
    交æīĢ
    0.08
    æ²ŁæĿij
    0.07
    说æĸĩ
    0.07
    ATUS
    0.07
    Activations Density 2.259%

    No Known Activations