© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48808
    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
    èĥĨ
    -0.09
    aglia
    -0.07
    ewise
    -0.07
    ynu
    -0.07
    æĮ¤
    -0.07
    ×Ĺת
    -0.07
    ievi
    -0.07
    ronics
    -0.06
    æŃ¢
    -0.06
    !“
    -0.06
    POSITIVE LOGITS
    bacher
    0.07
    婧
    0.07
    åħĪæĿ¥
    0.07
    åħĭæĭī
    0.07
     ìĤŃ
    0.07
    客æĪ·åħ³ç³»
    0.06
    大家è¦ģ
    0.06
     ausw
    0.06
    dere
    0.06
    转头
    0.06
    Activations Density 0.000%

    No Known Activations