© 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. 15695
    Prev
    Next
    INDEX
    Explanations

    hyphenated words like SG02, SG01, or general terms like SG

    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
     Wade
    -0.07
    ewood
    -0.06
     acc
    -0.06
    ä¸įçģŃ
    -0.06
    .Async
    -0.06
    å¾Ī好
    -0.06
    zni
    -0.06
    é£ŀå¥Ķ
    -0.06
     Bast
    -0.06
    ML
    -0.06
    POSITIVE LOGITS
     invece
    0.09
    mere
    0.08
     hingegen
    0.08
     meramente
    0.08
    à¹īà¸Ļ
    0.08
    éĶĻçļĦ
    0.08
    enix
    0.08
    ä»ĸåıªæĺ¯
    0.08
    ehler
    0.08
    less
    0.08
    Activations Density 0.578%

    No Known Activations