© 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. 27459
    Prev
    Next
    INDEX
    Explanations

    an article followed by description

    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
    å¿ĥ仪
    -0.08
     thereafter
    -0.08
    mpp
    -0.08
    tiers
    -0.08
    utam
    -0.08
    uten
    -0.07
     ìĿ´ëĬĶ
    -0.07
    è®
    -0.07
    osaic
    -0.07
    VertexAttrib
    -0.07
    POSITIVE LOGITS
     classic
    0.08
    æĪijåIJĹ
    0.07
     rather
    0.07
    ãģĤãģı
    0.07
     fairly
    0.07
    åħ¸åŀĭçļĦ
    0.07
    åĽŀäºĭ
    0.07
     typical
    0.07
    ä¸ĢåĽŀäºĭ
    0.07
     quite
    0.06
    Activations Density 0.069%

    No Known Activations