© 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. 33662
    Prev
    Next
    INDEX
    Explanations

    closing punctuation and braces

    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
    éĤ£ä¹Īè¿Ļ个
    -0.07
    holm
    -0.07
    ries
    -0.07
    èĮ¬
    -0.07
    -gnu
    -0.07
    weif
    -0.07
    -indent
    -0.07
    ÃŃcolas
    -0.07
    /interface
    -0.07
    имо
    -0.07
    POSITIVE LOGITS
    èī¯æľº
    0.06
    اش
    0.06
    åĵ©
    0.06
    ekte
    0.06
    asc
    0.06
    tera
    0.06
    inz
    0.06
    ysz
    0.06
    饱
    0.06
    åħ¶æŀĹ
    0.06
    Activations Density 0.023%

    No Known Activations