© 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. 19472
    Prev
    Next
    INDEX
    Explanations

    `// Code`

    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
    åħ¶ä½Ļ
    -0.08
    toc
    -0.08
    ilai
    -0.08
     gesta
    -0.07
    abee
    -0.07
    sut
    -0.07
    âĹĭ
    -0.07
    ardin
    -0.07
     ê·¸ê²Į
    -0.07
    жиÑĤ
    -0.07
    POSITIVE LOGITS
    究
    0.07
    裹
    0.06
    å®ŀéĻħä¸Ĭ
    0.06
    åĬłä¹ĭ
    0.06
    被客æĪ·
    0.06
    åıªæĥ³
    0.06
    çIJĨæĢ§çļĦ
    0.06
    羣æŃ£æĬĬ
    0.06
    Actually
    0.06
    åħ¶å®ŀåľ¨
    0.06
    Activations Density 0.001%

    No Known Activations