© 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. 60623
    Prev
    Next
    INDEX
    Explanations

    mixture, mixing, materials, heterogeneous

    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
    é¤IJ饮管çIJĨæľīéĻIJåħ¬åı¸
    -0.08
    iedz
    -0.08
    ùy
    -0.08
    æĹłæĥħçļĦ
    -0.08
    stime
    -0.08
    enger
    -0.07
    æĹłæĥħ
    -0.07
    uline
    -0.07
    पà¥ģर
    -0.07
    apult
    -0.07
    POSITIVE LOGITS
    ç»ĦåĪĨ
    0.09
    ä»ĩ
    0.08
     mixture
    0.08
    æ··åIJĪ
    0.08
     mixing
    0.08
     segregation
    0.08
     homogeneous
    0.07
     Mixing
    0.07
    仲
    0.07
     segreg
    0.07
    Activations Density 0.009%

    No Known Activations