© 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. 46591
    Prev
    Next
    INDEX
    Explanations

    constructor calls after super

    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
    ials
    -0.08
    éĥ¨å°±
    -0.07
    oidal
    -0.07
    Ñģом
    -0.07
    /doc
    -0.07
    acular
    -0.07
    angg
    -0.07
    ×ķ×ij×Ķ
    -0.07
    Movement
    -0.06
    \\\\
    -0.06
    POSITIVE LOGITS
    æĤ¨è¦ģ
    0.08
    æ¯ıä¸Ģ个åѦçĶŁ
    0.07
    åįĩæģ¯
    0.07
    ĮĢ
    0.06
    Salvar
    0.06
    è¯´ä½ł
    0.06
    åħ¢åħ¢ä¸ļä¸ļ
    0.06
    _Call
    0.06
    ä½łäºĨ
    0.06
    æħĭ
    0.06
    Activations Density 0.014%

    No Known Activations