© 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. 31279
    Prev
    Next
    INDEX
    Explanations

    legal actions or dates

    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
     Wol
    -0.07
    ç´°
    -0.06
    sf
    -0.06
    件
    -0.06
    cki
    -0.06
    æĺİäºĨ
    -0.06
    è¿Ľä¸ĢæŃ¥äºĨ解
    -0.06
    ç»Ĩ
    -0.06
    纤
    -0.06
    åĬłä¸Ĭ
    -0.06
    POSITIVE LOGITS
     preliminar
    0.11
     preliminary
    0.10
     prelim
    0.10
    çļĦåīįæľŁ
    0.09
    åĪĿæŃ¥
    0.09
    ä¹ĭåĪĿ
    0.08
    åİŁå§ĭçļĦ
    0.08
    .getRaw
    0.08
    çİ°æľīçļĦ
    0.08
    Existing
    0.08
    Activations Density 0.337%

    No Known Activations