© 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. 49781
    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
    aner
    -0.09
    retty
    -0.08
    ontan
    -0.08
    ucho
    -0.07
    agno
    -0.07
    主管
    -0.07
     "\<
    -0.07
    avu
    -0.07
    agi
    -0.07
    å±ŀ
    -0.07
    POSITIVE LOGITS
    oe
    0.08
    umpah
    0.07
    èĢĮå¼Ĥ
    0.07
    atoria
    0.07
    izr
    0.07
    upy
    0.07
    IFS
    0.07
    åĮºéķ¿
    0.07
    jing
    0.06
    èĢĮåĸ»
    0.06
    Activations Density 0.000%

    No Known Activations