© 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. 34007
    Prev
    Next
    INDEX
    Explanations

    occupation numbers

    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
    寰
    -0.08
     ëijĶ
    -0.08
    模åħ·
    -0.08
    山海
    -0.07
    西éĽħ
    -0.07
    flation
    -0.07
    å¸Ń
    -0.07
    æĪİ
    -0.07
    å¦ĤæĦı
    -0.07
    edit
    -0.07
    POSITIVE LOGITS
    ieden
    0.08
    æĢģ
    0.08
    累累
    0.08
    urn
    0.08
     lifetime
    0.07
    Cascade
    0.07
     depleted
    0.07
    æŀĩæĿ·
    0.07
    radio
    0.07
     thermal
    0.07
    Activations Density 0.008%

    No Known Activations