© 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. 1678
    Prev
    Next
    INDEX
    Explanations

    filters and polarizing plates

    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
    umer
    -0.11
    èħ¾é£ŀ
    -0.08
    丰满
    -0.08
    åħ¬ç§ģ
    -0.08
     Scaling
    -0.07
    æĹ©çĨŁ
    -0.07
     scaling
    -0.07
    onder
    -0.07
    aleb
    -0.07
    è§Ħ模çļĦ
    -0.07
    POSITIVE LOGITS
     filters
    0.11
    -filter
    0.11
     filter
    0.11
    filters
    0.10
    Filter
    0.10
    /filter
    0.10
    filter
    0.10
    Filters
    0.10
    .filters
    0.10
     Filters
    0.10
    Activations Density 0.010%

    No Known Activations