© 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. 16140
    Prev
    Next
    INDEX
    Explanations

    load, shear, attack, current

    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
    ieb
    -0.08
    redits
    -0.07
    trait
    -0.07
    idem
    -0.06
    uru
    -0.06
    à¤ķà¥įत
    -0.06
    indic
    -0.06
    ç¦ģæŃ¢è½¬è½½
    -0.06
     СвеÑĢ
    -0.06
    _traits
    -0.06
    POSITIVE LOGITS
    vvm
    0.09
     exposure
    0.08
     Exposure
    0.08
    被迫
    0.07
     effective
    0.07
    çļĦæľīæķĪ
    0.07
    effective
    0.07
    uxt
    0.07
     opportunities
    0.07
    æľºä¼ļ
    0.07
    Activations Density 0.096%

    No Known Activations