© 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. 2596
    Prev
    Next
    INDEX
    Explanations

    often, usually, common

    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¿ħè¦ģæŶ
    -0.07
     typical
    -0.07
    èĭ¥æĺ¯
    -0.07
     sed
    -0.06
    orda
    -0.06
     potentially
    -0.06
    æľīäºĽäºĭ
    -0.06
    éĢļ常æĥħåĨµä¸ĭ
    -0.06
    uolo
    -0.06
    åĦ¿æŶ
    -0.06
    POSITIVE LOGITS
     reporta
    0.08
    好åĥıæĺ¯
    0.08
    éĺ¿æ£®
    0.08
    itm
    0.08
    ZE
    0.08
    æľīåħ³äºİ
    0.08
    acom
    0.07
    aba
    0.07
    ==(
    0.07
    om
    0.07
    Activations Density 0.071%

    No Known Activations