© 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. 21607
    Prev
    Next
    INDEX
    Explanations

    age or aged

    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
    agu
    -0.07
    设æ³ķ
    -0.07
    人å¤ļ
    -0.07
    åı¯æĥľäºĨ
    -0.07
    æĺ¯ä»Ģä¹Īåij¢
    -0.07
     Brewer
    -0.07
    etter
    -0.07
    neau
    -0.07
     lắm
    -0.06
    åıĪä¸įæĺ¯
    -0.06
    POSITIVE LOGITS
     appunto
    0.09
    otron
    0.07
    DOMNode
    0.07
    ISOString
    0.06
    ãĤ¦ãĥ³
    0.06
    leur
    0.06
     wÅĤaÅĽnie
    0.06
    iée
    0.06
    (layers
    0.06
     EDUCA
    0.06
    Activations Density 0.023%

    No Known Activations