© 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. 10427
    Prev
    Next
    INDEX
    Explanations

    recipes using Guinness

    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
     Lauderdale
    -0.07
     overst
    -0.07
    èļ¯
    -0.07
    lice
    -0.07
    è¢«ä¾ĽåºĶåķĨ
    -0.07
    vád
    -0.07
    æī¯
    -0.06
    说æľī
    -0.06
    ley
    -0.06
    oth
    -0.06
    POSITIVE LOGITS
    åķŁ
    0.08
    ç«Ńè¯ļ
    0.08
     apologise
    0.07
    onav
    0.07
    ollo
    0.07
    æĶ¾
    0.07
    é½
    0.07
    obili
    0.06
    èī²åĪĹ
    0.06
    åIJ¯
    0.06
    Activations Density 0.001%

    No Known Activations