© 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. 40889
    Prev
    Next
    INDEX
    Explanations

    macro vs micro

    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
    ooks
    -0.09
    ÙĨدÙĨ
    -0.08
     noqa
    -0.08
    è¡ĢçĹĩ
    -0.08
    ook
    -0.08
    æĽ¿å°¼
    -0.08
    bos
    -0.08
    éģĹçĹĩ
    -0.08
    MENTS
    -0.08
     ordini
    -0.08
    POSITIVE LOGITS
     ones
    0.12
     Ones
    0.07
    ersed
    0.06
     counterparts
    0.06
     one
    0.06
    ãģªãĤĤãģ®
    0.06
    åij¢
    0.06
    ettet
    0.06
    ior
    0.06
     b
    0.06
    Activations Density 0.280%

    No Known Activations