© 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. 64435
    Prev
    Next
    INDEX
    Explanations

    how to do

    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
    è¿ĺæĺ¯ä¸įéĶĻçļĦ
    -0.08
     Concep
    -0.07
    æķħäºĭæĥħèĬĤ
    -0.07
    æ²ĥ
    -0.07
    åŁºæľ¬æ¦Ĥ念
    -0.07
    aza
    -0.07
     menger
    -0.07
     пÑĢоÑĤивоп
    -0.06
    ä¸ĢåĢį
    -0.06
    .truth
    -0.06
    POSITIVE LOGITS
    æĢİæł·æīįèĥ½
    0.10
     efficiently
    0.09
    æĢİä¹ĪåĬŀ
    0.09
    à¹ĥหà¹īà¹Ħà¸Ķà¹ī
    0.09
    å¦Ĥä½ķæīįèĥ½
    0.09
    çļĦé«ĺæķĪ
    0.09
    _methods
    0.09
    -how
    0.09
    æĢİ麼辦
    0.09
    Methods
    0.09
    Activations Density 2.001%

    No Known Activations