© 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. 34686
    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
    olver
    -0.07
    aldo
    -0.07
    çľī
    -0.06
    ARSE
    -0.06
    oth
    -0.06
    -other
    -0.06
    ito
    -0.06
     reminds
    -0.06
    æĸĵ
    -0.06
    æıIJéĨĴæĤ¨
    -0.06
    POSITIVE LOGITS
    çªģåĩºè´¡çĮ®
    0.09
    以ä¸ĬåĨħ容
    0.08
    ç»ĵåIJĪèĩªèº«
    0.08
    èĦļæŃ¥
    0.07
    bove
    0.07
    对该
    0.07
    为该
    0.07
    waran
    0.07
    以ä¸Ĭ
    0.07
    _HAL
    0.07
    Activations Density 0.010%

    No Known Activations