© 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. 51743
    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
    idan
    -0.08
    į¼
    -0.08
    inke
    -0.07
    äºĭåħ³
    -0.07
    ruÄį
    -0.07
    idet
    -0.07
    èī²åĪĹ
    -0.07
    æŃ»çļĦ
    -0.07
    idar
    -0.07
     Ấ
    -0.07
    POSITIVE LOGITS
    ÑģÑĤв
    0.06
    å·¥ç¨ĭçŃī
    0.06
    anca
    0.06
    æ¾İ
    0.06
    éĥ½åįģåĪĨ
    0.06
    udy
    0.06
    Increment
    0.06
    çİĦæѦ
    0.06
    çŃ¹
    0.06
    åįıåķĨ解åĨ³
    0.06
    Activations Density 0.000%

    No Known Activations