© 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. 13606
    Prev
    Next
    INDEX
    Explanations

    string literals or code blocks

    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
    ceau
    -0.08
     goût
    -0.07
     tastes
    -0.07
     représ
    -0.07
    åįĬæŃ¥
    -0.07
    åıįè§Ĥ
    -0.07
    NodeType
    -0.07
     Ponti
    -0.07
    ará
    -0.07
    主é¢ĺåħļæĹ¥æ´»åĬ¨
    -0.07
    POSITIVE LOGITS
    ¯
    0.07
    两ä¸ī
    0.07
     pa
    0.07
    asons
    0.07
    æłĹ
    0.06
    ount
    0.06
     Rug
    0.06
    çĿ¦
    0.06
    0.06
    pa
    0.06
    Activations Density 0.269%

    No Known Activations