© 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. 50764
    Prev
    Next
    INDEX
    Explanations

    lead

    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
    ation
    -0.08
    åĬłæĭ¿å¤§
    -0.08
    ä¸ĢåĽŀäºĭ
    -0.07
    ych
    -0.07
    grily
    -0.07
    amil
    -0.07
    plevel
    -0.07
    ifiable
    -0.07
    à¹Ģà¸ŀิà¹Īมà¸Ķà¹īวย
    -0.07
    edale
    -0.07
    POSITIVE LOGITS
    lessly
    0.10
     vá»±c
    0.09
    edly
    0.09
    erness
    0.08
    urang
    0.08
    ValuePair
    0.08
    reich
    0.08
    uard
    0.08
     tảng
    0.08
    attore
    0.07
    Activations Density 0.109%

    No Known Activations