© 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. 24874
    Prev
    Next
    INDEX
    Explanations

    little confused

    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
    人家
    -0.08
    æľ¬å¸Ĥ
    -0.07
    plib
    -0.07
    Ùıع
    -0.07
    æģĭ
    -0.07
    cook
    -0.07
     fisse
    -0.07
    ynet
    -0.07
    å°¾
    -0.07
    _offsets
    -0.07
    POSITIVE LOGITS
    èŃ°
    0.07
    客æľįçĥŃ线
    0.07
    Overview
    0.07
    å©ķ
    0.07
    ä¸ĭåĪĹéĹ®é¢ĺ
    0.07
    Ù¾ÛĮ
    0.07
    atur
    0.06
    ponder
    0.06
    andi
    0.06
     Jr
    0.06
    Activations Density 0.001%

    No Known Activations