© 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. 10900
    Prev
    Next
    INDEX
    Explanations

    handle invalid error

    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
    i
    -0.10
    kert
    -0.08
    o
    -0.08
    à¸ķà¹Į
    -0.08
    à§ĩ
    -0.07
    çļĦ
    -0.07
    ìĿĦ
    -0.07
    vironment
    -0.07
    ,
    -0.07
    iog
    -0.07
    POSITIVE LOGITS
    gether
    0.10
    odore
    0.10
    adays
    0.09
    eba
    0.09
    edException
    0.09
    innen
    0.09
    壮æĹıèĩªæ²»åĮº
    0.09
    ãģ£ãģ¦ãģ¿ãģŁ
    0.08
    iteDatabase
    0.08
    ông
    0.08
    Activations Density 0.005%

    No Known Activations