© 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. 11913
    Prev
    Next
    INDEX
    Explanations

    click on link or button

    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
    ietf
    -0.07
    psilon
    -0.07
     liá»ĩu
    -0.07
    ulton
    -0.07
    ifold
    -0.07
    afil
    -0.07
    unner
    -0.07
    änder
    -0.07
    üns
    -0.07
    微信æī«çłģ
    -0.07
    POSITIVE LOGITS
    ivity
    0.10
    ¿
    0.08
    tiv
    0.07
    worthy
    0.07
    nown
    0.07
    ยà¹īำ
    0.07
    öz
    0.07
    ä¸Ģãģ¤
    0.07
    ä¸Ģ声
    0.07
    åĩłä¸ĭ
    0.06
    Activations Density 0.058%

    No Known Activations