© 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. 62892
    Prev
    Next
    INDEX
    Explanations

    reference numbers

    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
    ↵
    -0.06
    çĵľ
    -0.06
     rematch
    -0.06
     diss
    -0.06
     "
    -0.06
    ัà¸ģ
    -0.06
    èĩ¨
    -0.06
    kbd
    -0.05
    åIJ»
    -0.05
    åIJį
    -0.05
    POSITIVE LOGITS
    emodel
    0.09
    Ỽm
    0.08
    æĹłéĻIJçļĦ
    0.08
    è¿Ļä¸Ģ次çļĦ
    0.08
    ERO
    0.08
    neb
    0.08
    ongan
    0.08
    笼
    0.08
    kü
    0.08
    CellStyle
    0.08
    Activations Density 0.010%

    No Known Activations