© 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. 30332
    Prev
    Next
    INDEX
    Explanations

    copyright protection

    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
    onde
    -0.09
    ÏĢιÏĥ
    -0.08
    anyag
    -0.08
    ickle
    -0.07
    wis
    -0.07
    itu
    -0.07
    dei
    -0.07
    iek
    -0.07
    Åijk
    -0.07
    涨è·Įå¹ħ
    -0.07
    POSITIVE LOGITS
    /*
    0.07
    åĢį
    0.07
    åħ¥
    0.07
    _direct
    0.07
    æĭīå¾·
    0.06
    /--
    0.06
    urang
    0.06
    çĹķ
    0.06
     ende
    0.06
     turned
    0.06
    Activations Density 0.009%

    No Known Activations