© 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. 39279
    Prev
    Next
    INDEX
    Explanations

    I need

    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
    éĺµ
    -0.07
    åIJĦåħ·
    -0.06
    quel
    -0.06
     paradox
    -0.06
     Hood
    -0.06
    xda
    -0.06
    ambo
    -0.06
     комбина
    -0.06
     epis
    -0.06
    èµ
    -0.06
    POSITIVE LOGITS
    çĤ¹åĩ»æŁ¥çľĭ
    0.08
    na
    0.08
    æıIJ示信æģ¯
    0.07
    çľĭä¸įåĩº
    0.07
    ãģłãĤįãģĨ
    0.07
    fels
    0.07
    å°½åľ¨
    0.07
    ẽ
    0.07
    inz
    0.07
    alainen
    0.07
    Activations Density 0.023%

    No Known Activations