© 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. 38969
    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
    çĹĺ
    -0.07
    è¯Ĭ
    -0.07
    åĿı
    -0.06
     certain
    -0.06
    éĢ¼
    -0.06
    ↵
    -0.06
    stead
    -0.06
    亲åĴĮ
    -0.06
    bot
    -0.06
    ä»İèĢĮ
    -0.06
    POSITIVE LOGITS
    Õ¦
    0.08
     muestr
    0.08
    建æĸ°
    0.08
    ÏĦικο
    0.08
    راز
    0.08
    wij
    0.07
    æ¯Ķäºļ
    0.07
    UNT
    0.07
    ertas
    0.07
    itations
    0.07
    Activations Density 0.000%

    No Known Activations