© 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. 55683
    Prev
    Next
    INDEX
    Explanations

    income, fees, taxes, costs

    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
    ricos
    -0.09
    åĪ°åºķæľīå¤ļ
    -0.08
    ãĤ³ãĥł
    -0.07
    æ¡£æ¡Ī管çIJĨ
    -0.07
    arity
    -0.07
    vore
    -0.07
    boh
    -0.07
    å¯Įç¿ģ
    -0.07
    avras
    -0.07
    rtype
    -0.07
    POSITIVE LOGITS
     contributions
    0.09
    以åıĬåħ¶ä»ĸ
    0.09
    主è¦ģåĮħæĭ¬
    0.08
    å°ijéĩıçļĦ
    0.08
    ä¹ŁåĮħæĭ¬
    0.08
     stuff
    0.08
    è¿ĺåĮħæĭ¬
    0.08
    ä¸Ģéĥ¨åĪĨ
    0.08
    鼶æĺŁ
    0.08
    åIJĦç§į
    0.08
    Activations Density 0.023%

    No Known Activations