© 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. 25923
    Prev
    Next
    INDEX
    Explanations

    под / ÐŁÐ¾Ð´ / ad / för

    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
    ohlen
    -0.09
    λάÏĩιÏĥ
    -0.09
    folge
    -0.08
    iggio
    -0.08
    geber
    -0.08
    onsin
    -0.08
    воло
    -0.07
    ssia
    -0.07
    unce
    -0.07
    istic
    -0.07
    POSITIVE LOGITS
     Ñģобой
    0.07
    å¾Ĺä½ı
    0.07
    è¡«
    0.07
    åļ
    0.07
     sheer
    0.07
     whom
    0.06
    çĿĢä¸Ģ
    0.06
    word
    0.06
    ä¸įä½ıçļĦ
    0.06
    ä¹Łç½¢
    0.06
    Activations Density 0.064%

    No Known Activations