© 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. 33634
    Prev
    Next
    INDEX
    Explanations

    unnamed entities

    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
    ä¸ĬåĬł
    -0.08
    assi
    -0.07
    VN
    -0.07
    .Fields
    -0.07
    ometimes
    -0.07
    轰鸣
    -0.07
    姬
    -0.07
    iju
    -0.07
     themselves
    -0.06
    ellant
    -0.06
    POSITIVE LOGITS
     ëijĶ
    0.08
     tepatnya
    0.08
    横
    0.08
    alem
    0.08
    æİ¥è¿ij
    0.07
     existence
    0.07
     unnamed
    0.07
    éĿłè¿ij
    0.07
    Exists
    0.07
    åĶ¯ä¸ĢçļĦ
    0.07
    Activations Density 0.002%

    No Known Activations