© 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. 48024
    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
    èħ»
    -0.06
    adrat
    -0.06
    éĩij森
    -0.06
    足ä¸įåĩºæĪ·
    -0.06
    ODEV
    -0.06
    imb
    -0.06
    è·Ŀä»Ĭ
    -0.06
     Wise
    -0.06
    artement
    -0.06
    move
    -0.06
    POSITIVE LOGITS
    eru
    0.07
    exas
    0.07
    ãĥªãĥ¼ãĤº
    0.07
    er
    0.07
    èĻ½æĺ¯
    0.07
    æīĢæĢĿ
    0.07
    OutputStream
    0.06
    ugna
    0.06
    ONGO
    0.06
    ivs
    0.06
    Activations Density 0.000%

    No Known Activations