© 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. 23178
    Prev
    Next
    INDEX
    Explanations

    actions reported in past tense

    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
    oud
    -0.08
    å¾ĹåĪ°ä¸Ģ个
    -0.07
     namanya
    -0.07
    kamp
    -0.07
    åıĪä»İ
    -0.07
    WithError
    -0.07
     seques
    -0.07
    Ñģловно
    -0.07
    ÑĤво
    -0.07
    áŀ·
    -0.07
    POSITIVE LOGITS
    åħ³äºİæĪij们
    0.08
     asupra
    0.08
    åį³éĢĿ
    0.08
     behalf
    0.07
    çļĦæīĢæľīæĸĩåŃĹ
    0.07
    หวà¹Īาà¸ĩ
    0.07
     تجاÙĩ
    0.07
     privire
    0.06
    æ®Ĩå°½
    0.06
    arden
    0.06
    Activations Density 0.436%

    No Known Activations