© 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. 62319
    Prev
    Next
    INDEX
    Explanations

    attribute assignment

    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
    mean
    -0.08
    åħ±äº§
    -0.07
    sher
    -0.07
    人çĶŁä¸Ń
    -0.07
    elves
    -0.07
    æĢ»åĢ¼
    -0.07
    semble
    -0.07
    åĪĨåĪ«åľ¨
    -0.06
    åħ±è®¡
    -0.06
    èĢ½
    -0.06
    POSITIVE LOGITS
     none
    0.08
    AccessType
    0.07
     moderately
    0.07
    Type
    0.07
    __/
    0.07
     either
    0.07
    à¹ģà¸ļà¸ļ
    0.07
    lopen
    0.07
    cio
    0.07
    ä¸ĢèĪ¬æĺ¯
    0.07
    Activations Density 0.378%

    No Known Activations