© 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. 46180
    Prev
    Next
    INDEX
    Explanations

    care cascade

    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
    åħ°
    -0.08
    주ìĿĺ
    -0.07
    اÛĮØ´
    -0.07
    arer
    -0.07
    æĥľ
    -0.07
    >*
    -0.07
     conting
    -0.07
    arella
    -0.07
    jun
    -0.06
    çļĦçī©è´¨
    -0.06
    POSITIVE LOGITS
    æ±ķ
    0.07
    徨
    0.07
    æµ¦æ±Ł
    0.06
    urgi
    0.06
    ç»Ħç»ĩä¸Ń
    0.06
    roe
    0.06
    uffici
    0.06
    çł´
    0.06
    akens
    0.06
    åľ¨è¿Ļ次
    0.06
    Activations Density 0.264%

    No Known Activations