© 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. 31700
    Prev
    Next
    INDEX
    Explanations

    recognising beauty, insects, Facebook, publication, snowstorm, dividend, investing

    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
    orra
    -0.09
    ัà¸ĩà¸ģ
    -0.08
    acu
    -0.08
    sdale
    -0.08
    ãĥ¼ãĤ¸ãĥ¥
    -0.08
    iagnostics
    -0.08
    ucha
    -0.07
    ำà¸Ļ
    -0.07
    wares
    -0.07
    .EN
    -0.07
    POSITIVE LOGITS
    rin
    0.07
     Har
    0.06
    åħ·æľīèī¯å¥½çļĦ
    0.06
    èĨľçĤİ
    0.06
    ugh
    0.06
    æľīå¤ļ
    0.06
    æľīä½Ļ
    0.06
    æ¯Ķåħ¶ä»ĸ
    0.06
     practise
    0.06
     Cos
    0.06
    Activations Density 0.002%

    No Known Activations