© 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. 42930
    Prev
    Next
    INDEX
    Explanations

    just learned knowledge

    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
    è¾¹éĻħ
    -0.07
    ØŃاÙĦ
    -0.07
    à¹Īà¸Ńย
    -0.07
    满足ä¸įåIJĮ
    -0.07
    guer
    -0.07
    å¦Ĥæ¶īåıĬ
    -0.07
    typings
    -0.07
     ÏĢάν
    -0.07
    inity
    -0.07
    å¦Ĥ约
    -0.07
    POSITIVE LOGITS
    æīĢåѦ
    0.10
    æīĢåѦçļĦ
    0.09
    åīįéĿ¢
    0.08
     newfound
    0.08
    åĪļæīį
    0.08
    åľ¨åīįéĿ¢
    0.08
     previously
    0.07
     learnt
    0.07
    learn
    0.07
    aoke
    0.07
    Activations Density 0.022%

    No Known Activations