© 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. 39846
    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
    usel
    -0.07
    elp
    -0.06
    æĭ¾
    -0.06
    Ñļ
    -0.06
     unp
    -0.06
    ä»İåīį
    -0.06
    级çļĦ
    -0.06
    åĬ¡
    -0.06
    å¾Ħ
    -0.06
    idual
    -0.06
    POSITIVE LOGITS
    饶
    0.08
    éĩijèĬ±
    0.08
    atoi
    0.08
    å·²ç»ıæľī
    0.07
    è¡Ŀ
    0.07
     viewType
    0.07
    rd
    0.07
    ä¹¾åĿ¤
    0.07
    SingleNode
    0.07
    ott
    0.07
    Activations Density 0.000%

    No Known Activations