© 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. 46810
    Prev
    Next
    INDEX
    Explanations

    months and years

    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
    çºĤ
    -0.08
    çĤľ
    -0.07
    anning
    -0.07
    ால
    -0.07
    ial
    -0.07
    é©
    -0.07
    ç§ijæĬĢèĤ¡ä»½æľīéĻIJåħ¬åı¸
    -0.07
    ry
    -0.07
    æĢ»æ¯Ķ
    -0.07
     counterpart
    -0.07
    POSITIVE LOGITS
     previous
    0.12
     пÑĢедÑĭ
    0.11
    previous
    0.10
    åīįä¸Ģ
    0.10
    æѤåīįçļĦ
    0.10
    ä¸Ĭä¸Ģ个
    0.10
     vorig
    0.09
    ä¹ĭåīįçļĦ
    0.09
    åīįéĿ¢çļĦ
    0.09
     пÑĢеж
    0.09
    Activations Density 0.395%

    No Known Activations