© 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. 47424
    Prev
    Next
    INDEX
    Explanations

    filter

    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
    lave
    -0.09
    лиÑĤа
    -0.09
    лÑĸв
    -0.09
    cie
    -0.08
    adera
    -0.08
    æĹ¥åĪ¶
    -0.08
    ä¸İæݧåĪ¶
    -0.08
    indle
    -0.08
    uilder
    -0.08
    agnet
    -0.08
    POSITIVE LOGITS
     filtering
    0.11
     filters
    0.10
     filter
    0.10
     Filtering
    0.09
    è¿ĩ滤
    0.09
    -filter
    0.09
    éļľ
    0.09
     intervening
    0.08
    filters
    0.08
     Filters
    0.08
    Activations Density 0.033%

    No Known Activations