© 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. 47151
    Prev
    Next
    INDEX
    Explanations

    X Y phrases

    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
    otton
    -0.07
    pector
    -0.07
     Amazon
    -0.07
    æĺ¯éĩĩçĶ¨
    -0.07
    sic
    -0.06
    æĪĸå°ij
    -0.06
    åį´æľī
    -0.06
    æµ·é»ĺ
    -0.06
    ç»ĵè¯Ń
    -0.06
    åıªè§īå¾Ĺ
    -0.06
    POSITIVE LOGITS
    é¦ĸåħĪéľĢè¦ģ
    0.07
    齡
    0.07
     kidd
    0.07
    ièrement
    0.07
    å°¼å°Ķ
    0.07
    cking
    0.07
    ãĤ»ãĥ³
    0.07
    ikum
    0.07
    usti
    0.06
    à¸Ńยู
    0.06
    Activations Density 0.026%

    No Known Activations