© 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. 4298
    Prev
    Next
    INDEX
    Explanations

    states of being or conditions

    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
     hereby
    -0.06
    anging
    -0.06
    åĪĻ
    -0.06
    åĪĻå°Ĩ
    -0.06
     however
    -0.06
    åīĩ
    -0.06
    åĪĻçĶ±
    -0.06
    å§ľ
    -0.06
    è¿ŀæİ¥æľī
    -0.06
    éķ¿ä¸īè§Ĵ
    -0.06
    POSITIVE LOGITS
    æĪĸåħ¶
    0.12
    åĴĮåĪ«äºº
    0.09
    æľĢåIJİæĺ¯
    0.08
    åĴĮåħ¶
    0.08
    è¿Ļéĥ½æĺ¯
    0.08
     именно
    0.08
    uesta
    0.08
    ologio
    0.08
    cula
    0.08
    AREST
    0.08
    Activations Density 0.199%

    No Known Activations