© 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. 65245
    Prev
    Next
    INDEX
    Explanations

    national counterparts

    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
    ä¸ļçļĦ
    -0.08
    ائØŃ
    -0.07
    ç«ĭçļĦ
    -0.07
    äºĭæĥħ
    -0.07
    ipel
    -0.07
    žd
    -0.06
    uccio
    -0.06
    åĽ¢çļĦ
    -0.06
    ç»ı缸åħ³éĥ¨éŨæī¹åĩĨ
    -0.06
     Celle
    -0.06
    POSITIVE LOGITS
     counterpart
    0.10
     counterparts
    0.09
    åľ°ä½į
    0.08
    ailability
    0.07
    ä¸İåIJ¦
    0.07
    puties
    0.07
    åIJĪä½ľçĶ¨
    0.07
    åĮĸåıijå±ķ
    0.07
    iqueta
    0.07
    使å®ĥ
    0.07
    Activations Density 0.225%

    No Known Activations