© 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. 45674
    Prev
    Next
    INDEX
    Explanations

    technical field

    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
    edException
    -0.08
    à¹Ī
    -0.08
    ÖĤ
    -0.07
    à¸īะà¸Ļัà¹īà¸Ļ
    -0.07
    atok
    -0.07
    intang
    -0.07
    angkal
    -0.07
    edList
    -0.07
    нин
    -0.07
    Äĩe
    -0.07
    POSITIVE LOGITS
    ity
    0.12
    ities
    0.09
    ulty
    0.08
    ìłģìĿ¸
    0.08
    isht
    0.08
     lưỡng
    0.08
    ingen
    0.08
    /legal
    0.08
    orr
    0.07
     ÙĦÙĦغاÙĬØ©
    0.07
    Activations Density 0.021%

    No Known Activations