© 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. 25550
    Prev
    Next
    INDEX
    Explanations

    numbers, currency, and punctuation

    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
     médi
    -0.08
    æģ¶éŃĶ
    -0.06
    irate
    -0.06
    ppe
    -0.06
    elow
    -0.06
    AAAAAAAA
    -0.06
    ÑijÑĢ
    -0.06
    uÄĩ
    -0.06
     impl
    -0.06
    ece
    -0.06
    POSITIVE LOGITS
    ogat
    0.08
    天ä¸ĭçļĦ
    0.07
    hunter
    0.07
    ostat
    0.07
    çĭĻ
    0.07
    ä»Ģ
    0.07
    peri
    0.07
    ounter
    0.07
    èĿ¦
    0.07
    ijs
    0.07
    Activations Density 0.822%

    No Known Activations