© 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. 27113
    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
    èݱæĸ¯
    -0.08
    ihan
    -0.08
     tenden
    -0.08
     vicenda
    -0.07
    idão
    -0.07
    ashi
    -0.07
    zis
    -0.07
    ÙĤÙĬÙĤ
    -0.07
    ä¼ģä¸ļåħ¬ç¤º
    -0.07
    getOption
    -0.07
    POSITIVE LOGITS
    yen
    0.07
    .web
    0.06
    bev
    0.06
    _below
    0.06
    å§Ķ
    0.06
     spend
    0.06
    å¯ĩ
    0.06
    ory
    0.06
    ant
    0.06
     '^
    0.06
    Activations Density 0.000%

    No Known Activations