© 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. 32691
    Prev
    Next
    INDEX
    Explanations

    physical actions and objects

    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
    æĢ§æĪĸ
    -0.08
    sob
    -0.07
    ä¹ĭæľĢ
    -0.06
    æĹ¥çĶŁ
    -0.06
    èıģ
    -0.06
    åľ°è¡¨
    -0.06
    æĪĸ被
    -0.06
    usak
    -0.06
    oczy
    -0.06
    æľ¬ç§ijæ¯ķä¸ļçĶŁ
    -0.06
    POSITIVE LOGITS
    è¿Ļä¹Īç®Ģåįķ
    0.08
    è¿Ļæł·ä¸Ģ个
    0.08
    ãģ¨ãģĦãģĨ
    0.08
    ä½ľä¸ºä¸Ģ项
    0.07
     kia
    0.07
    iÄĩ
    0.07
    åħ³ç³»åĪ°
    0.07
    åħ³ä¹İ
    0.07
    ä½ľä¸ºä¸Ģç§į
    0.07
    ilog
    0.07
    Activations Density 0.095%

    No Known Activations