© 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. 17219
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ocab
    -0.08
    con
    -0.07
    家åºŃçĶŁæ´»
    -0.06
    olt
    -0.06
     Moo
    -0.06
    à¸ģระà¸Ĺ
    -0.06
    éĩijä¸Ŀ
    -0.06
    Ñħова
    -0.06
    æłĸ
    -0.06
    ering
    -0.06
    POSITIVE LOGITS
    arth
    0.08
    ARTH
    0.07
    igni
    0.07
    æĭľ
    0.07
     respecting
    0.07
    arty
    0.07
    ograma
    0.07
    ä»»ä½ł
    0.07
    è¦ģäºĨ解
    0.07
    æĢ»åĢ¼
    0.07
    Activations Density 0.000%

    No Known Activations