© 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. 33494
    Prev
    Next
    INDEX
    Explanations

    comparison than expected

    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
     möglichst
    -0.08
    à¦ļার
    -0.08
    ä»Ģä¹Īæł·çļĦ人
    -0.08
    ðŁĻĤ
    -0.08
    ä»Ģä¹Īæł·çļĦ
    -0.08
    è¶Ĭæĺ¯
    -0.08
    èĩ³åħ³
    -0.08
    eda
    -0.08
    æķĻèĤ²äºĭä¸ļ
    -0.08
    dbh
    -0.08
    POSITIVE LOGITS
     بÙĥØ«ÙĬر
    0.09
     typical
    0.09
    大å¤ļæķ°
    0.08
     usual
    0.08
    常è§Ħ
    0.08
    ä»»ä½ķä¸Ģç§į
    0.07
    å®ŀéĻħéľĢæ±Ĥ
    0.07
    许å¤ļ
    0.07
    our
    0.07
    æīĢèĥ½
    0.07
    Activations Density 0.107%

    No Known Activations