© 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. 58539
    Prev
    Next
    INDEX
    Explanations

    citations and code snippets

    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
    kbd
    -0.08
    udu
    -0.08
    วà¹Īาà¸ĩ
    -0.08
    amah
    -0.07
    缸åħ³èµĦ讯
    -0.07
    çļĦæĹ¥åŃIJ
    -0.07
    该å±Ģ
    -0.07
    uben
    -0.07
    ubo
    -0.07
    çĹ«
    -0.07
    POSITIVE LOGITS
    &
    0.08
    åĽ½
    0.07
     parl
    0.07
    ÏĦÏģι
    0.06
    abol
    0.06
    ader
    0.06
    abel
    0.06
    ı
    0.06
    GB
    0.06
    ISTIC
    0.06
    Activations Density 0.012%

    No Known Activations