© 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. 16251
    Prev
    Next
    INDEX
    Explanations

    strip mining, column, clubs, blade

    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
    ÅĽwiÄĻ
    -0.10
    ãģ¾ãģ¾
    -0.09
    ãģĹãģıãģ¯
    -0.09
    รà¹īาย
    -0.09
    stuk
    -0.09
    iable
    -0.09
    lighet
    -0.08
    uccio
    -0.08
    enz
    -0.08
    çIJ²
    -0.08
    POSITIVE LOGITS
    ÑģÑı
    0.10
    ness
    0.07
    جاع
    0.07
    ington
    0.07
    nyder
    0.07
     tangan
    0.06
    毫
    0.06
    edImage
    0.06
    åīĤ
    0.06
    araf
    0.06
    Activations Density 0.062%

    No Known Activations