© 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. 19390
    Prev
    Next
    INDEX
    Explanations

    distances between measured things

    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
     pales
    -0.08
    æ¯ıå¹³æĸ¹ç±³
    -0.07
    äºĮåįģ大
    -0.07
    cé
    -0.07
    agam
    -0.07
    èĮĥåĽ´åĴĮ
    -0.07
    çļĦ太éĺ³
    -0.07
    ople
    -0.07
    uduk
    -0.07
    ILLS
    -0.07
    POSITIVE LOGITS
    åIJijåIJİ
    0.08
     distance
    0.07
    è·Ŀ离
    0.07
    endas
    0.07
    æ¸ħç®Ĺ
    0.07
    è·ĿéĽ¢
    0.07
    å¾Ģåīį
    0.07
    è½´è·Ŀ
    0.07
    space
    0.07
     offset
    0.07
    Activations Density 0.004%

    No Known Activations