© 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. 20222
    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
    lier
    -0.08
    lahan
    -0.08
    bst
    -0.07
    æ´Ľä¼Ĭ
    -0.07
    agam
    -0.07
    unlikely
    -0.07
    isset
    -0.07
     *_
    -0.07
    ongan
    -0.07
    ãģ®ãģĭãĤĤãģĹãĤĮ
    -0.07
    POSITIVE LOGITS
    俱ä¹IJéĥ¨
    0.08
    æĸ°åĬłåĿ¡
    0.07
    eer
    0.07
    缸è¾ħ缸æĪIJ
    0.07
    注æĦı
    0.07
    åĬłæĭ¿å¤§
    0.07
    大åIJĥä¸ĢæĥĬ
    0.07
    bacher
    0.06
    ORTE
    0.06
    éĢīå®ļ
    0.06
    Activations Density 0.000%

    No Known Activations