© 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. 10127
    Prev
    Next
    INDEX
    Explanations

    indices, capacity, temperature, protocol

    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
    âĨ³
    -0.08
    æĮĻ
    -0.08
    (&_
    -0.08
    ä¸įè¿ĩæĿ¥
    -0.08
    ittest
    -0.08
    epass
    -0.08
    ancier
    -0.08
    ambu
    -0.08
     Embed
    -0.07
     embedding
    -0.07
    POSITIVE LOGITS
    Âł
    0.10
    æłĩæĺİ
    0.06
    åīįè¿°
    0.06
    áĬ
    0.06
    éħ¬
    0.06
    ouch
    0.06
    éĺIJ
    0.06
    ogu
    0.06
    两
    0.06
     customary
    0.06
    Activations Density 0.003%

    No Known Activations