© 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. 39854
    Prev
    Next
    INDEX
    Explanations

    aesthetic aspects and preferences

    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
    ÑĩаÑĤ
    -0.08
    oz
    -0.08
    ллÑİ
    -0.07
    olland
    -0.07
    ngo
    -0.07
    stairs
    -0.07
    zana
    -0.07
    starter
    -0.07
    ocken
    -0.07
    ippy
    -0.06
    POSITIVE LOGITS
    åij³çļĦ
    0.08
    0.08
    ì©
    0.08
    -conscious
    0.08
    æĥħ趣
    0.07
    oppel
    0.07
    ÑģÑĤеÑĤ
    0.07
    acement
    0.07
    çļĦ追æ±Ĥ
    0.07
    æľ¨æĸ¯
    0.07
    Activations Density 0.008%

    No Known Activations