© 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. 56199
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols like $

    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
    holm
    -0.08
    åįģäºĮæĮĩ
    -0.08
    麾
    -0.08
    èĩ³å°ij
    -0.07
    æ¡ĥæĿİ
    -0.07
    å¾Ī大ç¨ĭ度ä¸Ĭ
    -0.07
    ç½ijçĬ¶
    -0.07
    æ¦Ī
    -0.07
    ä½ķçŃī
    -0.07
    ANC
    -0.07
    POSITIVE LOGITS
    koch
    0.07
    è¦ģä½ł
    0.07
     Example
    0.07
    ypi
    0.07
     exempl
    0.07
    ä¾ĭåŃIJ
    0.07
    ä¾ĭå¦Ĥ
    0.07
    ç´¯
    0.07
    åıĪå¦Ĥ
    0.07
     example
    0.07
    Activations Density 0.047%

    No Known Activations