© 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. 48115
    Prev
    Next
    INDEX
    Explanations

    generated code or files

    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
    /respond
    -0.08
    /tos
    -0.07
     sust
    -0.07
    InitStruct
    -0.07
    .TypeOf
    -0.06
    znak
    -0.06
    /stretchr
    -0.06
    ONUS
    -0.06
    å©
    -0.06
    vez
    -0.06
    POSITIVE LOGITS
     manually
    0.10
     exported
    0.09
    æīĭåĬ¨
    0.09
     freshly
    0.08
     generated
    0.08
     (`
    0.08
    enerated
    0.08
     `.
    0.08
     manual
    0.08
     batch
    0.08
    Activations Density 0.016%

    No Known Activations