© 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. 51666
    Prev
    Next
    INDEX
    Explanations

    names followed by possessives

    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
     пÑĢиз
    -0.07
    å¤Ń
    -0.07
     doubly
    -0.07
    ¤
    -0.07
    fér
    -0.07
    Ùĭ
    -0.06
    磼
    -0.06
    agit
    -0.06
    ä¸ĢçŃ¹
    -0.06
    inel
    -0.06
    POSITIVE LOGITS
    ares
    0.08
    åŃ¦å¹´åº¦
    0.08
    ATUS
    0.07
    主åĬ¨åIJij
    0.07
    åĽŀæĿ¥åIJİ
    0.07
    个人åį«çĶŁ
    0.07
    ä¹łæĥ¯æĢ§
    0.07
    icara
    0.07
    æĥ¯
    0.07
    OLUM
    0.07
    Activations Density 0.133%

    No Known Activations