© 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. 30655
    Prev
    Next
    INDEX
    Explanations

    emojis and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ians
    -0.08
    enus
    -0.08
    iong
    -0.07
    ÙĬÙĨ
    -0.07
     Kills
    -0.07
    inton
    -0.07
    ìn
    -0.07
    ije
    -0.07
    uy
    -0.07
    eni
    -0.07
    POSITIVE LOGITS
    ï¸ı
    0.14
    ï¸İ
    0.10
    0.10
    她表示
    0.08
    ลฯ
    0.07
    ħ
    0.07
    缸è¾ħ缸æĪIJ
    0.07
    ¤
    0.07
    gether
    0.07
    ãģıãģ¡ãĤĥ
    0.07
    Activations Density 0.003%

    No Known Activations