© 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. 43498
    Prev
    Next
    INDEX
    Explanations

    banks and albanian

    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
    -0.07
    åĹ
    -0.07
    (
    -0.07
    entially
    -0.07
    [
    -0.06
    “
    -0.06
    满
    -0.06
     “
    -0.06
     <
    -0.05
    é¡·
    -0.05
    POSITIVE LOGITS
    ä¹ĭçģ«
    0.09
    åIJĮä¸Ĭ
    0.09
    emergen
    0.09
     Insg
    0.08
    uploader
    0.08
    оÑģÑĤÑĢе
    0.08
    adz
    0.08
    å½Ńåįļ
    0.08
    arent
    0.08
    ķĮ
    0.08
    Activations Density 0.133%

    No Known Activations