© 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. 24892
    Prev
    Next
    INDEX
    Explanations

    successful professionals and brands

    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
    cac
    -0.08
    -prop
    -0.07
    اة
    -0.07
    èIJĮ
    -0.07
     Eag
    -0.07
    cium
    -0.07
    åħļæĢ§
    -0.07
    æĮĸæİĺåħ¬åı¸
    -0.06
    alay
    -0.06
    lash
    -0.06
    POSITIVE LOGITS
    æĪIJåĬŁç»ıéªĮ
    0.17
    æĪIJåĬŁæ¡Īä¾ĭ
    0.15
    æ¦ľæł·
    0.14
    æĪIJåĬŁçļĦ
    0.12
    èĮĥä¾ĭ
    0.12
     successful
    0.12
    æĪIJåĬŁ
    0.12
    åħ¸èĮĥ
    0.12
     exemplary
    0.12
    示èĮĥ
    0.12
    Activations Density 0.582%

    No Known Activations