© 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. 10345
    Prev
    Next
    INDEX
    Explanations

    author tag

    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
    èģ²
    -0.07
    绾ç»İ
    -0.07
    声
    -0.06
    çĪ½å¿«
    -0.06
    سات
    -0.06
    lipp
    -0.06
    سÙĬÙĨ
    -0.06
     sable
    -0.06
     lear
    -0.06
    endale
    -0.06
    POSITIVE LOGITS
     Autón
    0.07
    å®Ľ
    0.07
     Hin
    0.07
    aub
    0.07
    æģª
    0.07
    赫赫
    0.07
    çħ¦
    0.07
    ίκ
    0.07
    æľĿ天
    0.07
    ÃŃc
    0.07
    Activations Density 0.119%

    No Known Activations