© 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. 55686
    Prev
    Next
    INDEX
    Explanations

    bloating, distention, smooth muscle

    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
     transf
    -0.07
    è¾ĵè¡Ģ
    -0.07
    使çĶ¨å¯¿åij½éķ¿
    -0.07
    å»ºè®¾æľŁ
    -0.07
    UIScreen
    -0.07
    åį±éĻ©
    -0.07
    ä¿Ŀåºķ
    -0.07
    çĶĦåĪ«
    -0.07
     глазаÑħ
    -0.07
    åĭ§
    -0.06
    POSITIVE LOGITS
    ä¸įçķħ
    0.12
    éĺ»å¡ŀ
    0.10
    顺çķħ
    0.09
    ä¸įéĢļ
    0.09
    çķħéĢļ
    0.09
    éĢļçķħ
    0.09
    ä¸į顺
    0.09
    éĥģ
    0.09
    æ¢Ĺéĺ»
    0.09
    çIJĨ顺
    0.09
    Activations Density 0.002%

    No Known Activations