© 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. 60568
    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
    ElementException
    -0.07
    _mappings
    -0.07
     wah
    -0.06
    ambu
    -0.06
     domic
    -0.06
    认é¢Ĩ
    -0.06
    ValueCollection
    -0.06
    ู
    -0.06
    éºĹ
    -0.06
    å½»åºķ
    -0.06
    POSITIVE LOGITS
    ä¸ĩ件
    0.07
    ê¸ī
    0.07
    apel
    0.07
    ÙĤÙĦØ©
    0.07
    ãĥªãĥĨãĤ£
    0.07
    abh
    0.06
    红åı¶
    0.06
    æĸĩåѦéĻ¢
    0.06
    öhnen
    0.06
    _MATH
    0.06
    Activations Density 0.000%

    No Known Activations