© 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. 38702
    Prev
    Next
    INDEX
    Explanations

    ungual infections, gyro rotor, injuries, SI, rewrite, divided India

    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
    çĬ¯
    -0.08
    æľ¬åij½
    -0.08
    é»ijè±Ĩ
    -0.07
    ÏĨÏħ
    -0.07
    .Virtual
    -0.07
    .library
    -0.07
    çĬ¯çļĦ
    -0.07
    çľģä¸ĭ
    -0.07
    å¸Ĥ容
    -0.07
    -money
    -0.07
    POSITIVE LOGITS
    âĢij
    0.07
    éĢļè¿ĩæŃ¤æ¬¡
    0.07
     yana
    0.07
    âĢ
    0.06
    æĻ¤
    0.06
    çļĦåħ¨éĥ¨åĨħ容
    0.06
    é¼ĵ
    0.06
    rais
    0.06
    ffit
    0.06
    åľ¨æķ´ä¸ª
    0.06
    Activations Density 0.008%

    No Known Activations