© 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. 25465
    Prev
    Next
    INDEX
    Explanations

    filter data or lists

    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
    为ä»Ģä¹Ī说
    -0.08
     lâm
    -0.07
    Embedded
    -0.07
    ìĬµ
    -0.07
    åľĨ满çļĦ
    -0.07
    æ·¼
    -0.07
    okie
    -0.07
     oÄįek
    -0.06
     éché
    -0.06
    uede
    -0.06
    POSITIVE LOGITS
    çŃĽéĢī
    0.17
    è¿ĩ滤
    0.17
     filtering
    0.16
     filter
    0.16
    åīĶéĻ¤
    0.15
    /filter
    0.15
     filters
    0.15
     lá»įc
    0.14
     Filtering
    0.14
     Filter
    0.14
    Activations Density 0.174%

    No Known Activations