© 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. 46081
    Prev
    Next
    INDEX
    Explanations

    function definitions in Go

    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
    λιÏĥ
    -0.08
    mals
    -0.08
    머ëĭĪ
    -0.08
    ç¿ģ
    -0.08
    igm
    -0.07
    รา
    -0.07
    Ãłnh
    -0.07
    åħ¼æĢ»ç»ıçIJĨ
    -0.07
    ä¸įè¿ĩä»ĸ
    -0.07
     Lorem
    -0.07
    POSITIVE LOGITS
    天å®ĩ
    0.08
    zie
    0.07
    åħ¶
    0.06
    ´
    0.06
    åħ¶éģĵ
    0.06
    åħ¶ä¸İ
    0.06
    ¿
    0.06
    éģĵ
    0.06
    ÈĽ
    0.06
    天åı°
    0.06
    Activations Density 0.025%

    No Known Activations