© 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. 48488
    Prev
    Next
    INDEX
    Explanations

    Submitted February

    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
    laughter
    -0.07
    æµĨ
    -0.06
    ìĨĮ
    -0.06
    çĬ¹
    -0.06
    ä¸įè¿ĩæĿ¥
    -0.06
    èĬ³èįī
    -0.06
    _readable
    -0.06
    heim
    -0.06
    åѦçļĦ
    -0.06
    漿
    -0.05
    POSITIVE LOGITS
     ._
    0.08
    ä¸įæĥľ
    0.07
    SingleNode
    0.07
    θαν
    0.07
     
    0.07
    缼åħ¸
    0.07
    ?,?,
    0.07
    Hooks
    0.07
    eht
    0.07
    Interested
    0.06
    Activations Density 0.010%

    No Known Activations