© 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. 38199
    Prev
    Next
    INDEX
    Explanations

    number base conversions

    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
    ucia
    -0.08
    éĩı大
    -0.08
    ssen
    -0.07
    umi
    -0.07
     generation
    -0.07
    zsche
    -0.07
    दा
    -0.07
    soever
    -0.06
    dong
    -0.06
    dale
    -0.06
    POSITIVE LOGITS
    less
    0.10
    ãģĤãĤĬ
    0.09
    ä¸įæĺİçļĦ
    0.08
    à¹Ģà¸Ķียวà¸ģัà¸ļ
    0.07
     lineHeight
    0.07
    ymm
    0.07
    à¹Ģà¸Ķียวà¸ģัà¸Ļ
    0.07
    æľįåĬ¡åħ¬åı¸
    0.07
    igin
    0.07
    LESS
    0.07
    Activations Density 0.006%

    No Known Activations