© 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. 49311
    Prev
    Next
    INDEX
    Explanations

    you followed by what

    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
    adients
    -0.06
    æĺ¯ä¸Ģå¥Ĺ
    -0.06
    adders
    -0.06
    orsa
    -0.06
    æŁIJç§į
    -0.06
    åĶ¯ä¸Ģä¸Ģ个
    -0.06
     resto
    -0.06
    æĺ¯ä¸ĢéŨ
    -0.06
    çģµåĦ¿
    -0.06
    ikit
    -0.06
    POSITIVE LOGITS
    _ARG
    0.08
     briefly
    0.07
    åħĭ
    0.07
    åľ¨å¿ħ
    0.07
    echa
    0.07
    .parents
    0.06
     reasoning
    0.06
    åĢĭåĪ¥
    0.06
    åIJĦåŃ¦æł¡
    0.06
    軽ãģı
    0.06
    Activations Density 0.001%

    No Known Activations