© 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. 24098
    Prev
    Next
    INDEX
    Explanations

    surgical treatment or therapy

    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
    nud
    -0.08
    poi
    -0.07
    çµ®
    -0.07
    æ¬łç¨İåħ¬åijĬ
    -0.07
    è®¤çľŁå®ĮæĪIJ
    -0.07
     nud
    -0.07
     compilers
    -0.07
    èĪ
    -0.07
    ä»»æĢ¨
    -0.07
    åģ¥åº·ç½ij
    -0.07
    POSITIVE LOGITS
    æŀľæĸŃ
    0.11
     costly
    0.09
    毫ä¸įçĬ¹è±«
    0.08
    å¿ħè¦ģæŶ
    0.08
    å¤ĩéĢī
    0.08
    æĺĤè´µçļĦ
    0.08
    èĢĥèĻij
    0.08
    either
    0.08
     either
    0.08
    å¿ħè¦ģçļĦ
    0.08
    Activations Density 0.126%

    No Known Activations