© 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. 14721
    Prev
    Next
    INDEX
    Explanations

    X-Y wins

    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
    ëł¹
    -0.07
    ocere
    -0.07
    anen
    -0.07
    baru
    -0.06
    HTMLElement
    -0.06
    pedia
    -0.06
    ãĤĤãģ£ãģ¨
    -0.06
    orien
    -0.06
    Õ¡Õ°
    -0.06
    ลà¹Īะ
    -0.06
    POSITIVE LOGITS
    å¹´åįİ
    0.08
    ails
    0.07
    ott
    0.07
    ï¸İ
    0.07
    èĬ¸
    0.07
    /+
    0.07
    俱ä¹IJéĥ¨
    0.07
    ä¸ĭæŬ
    0.07
     shootout
    0.07
    enties
    0.07
    Activations Density 0.069%

    No Known Activations