© 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. 18062
    Prev
    Next
    INDEX
    Explanations

    contrast or binary outcomes

    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
    幸
    -0.07
    ide
    -0.07
    oko
    -0.07
     pr
    -0.06
     prim
    -0.06
     clad
    -0.06
     Prima
    -0.06
    å¾Ĵ
    -0.06
    udou
    -0.06
    çijļ
    -0.06
    POSITIVE LOGITS
    Ł
    0.09
     ê·¸ëłĩì§Ģ
    0.09
    .RunWith
    0.08
    ogs
    0.08
    åħ¥å®¤
    0.08
    rams
    0.08
    ãģĿãģĨãģ§
    0.08
     menolak
    0.08
    oviÄĩ
    0.08
    åħ¶ä»ĸåľ°åĮº
    0.08
    Activations Density 0.234%

    No Known Activations