© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30495
    Prev
    Next
    INDEX
    Explanations

    how to decide

    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
     Administration
    -0.09
     seber
    -0.08
    åľ¨æĹ¥å¸¸çĶŁæ´»ä¸Ń
    -0.08
     administration
    -0.07
    _CHARACTER
    -0.07
     Chance
    -0.07
    è¡ĮæĶ¿
    -0.07
     overd
    -0.07
    posit
    -0.07
    loed
    -0.07
    POSITIVE LOGITS
    çģµæ´»çļĦ
    0.08
    è¡Įä¹ĭ
    0.08
    åģļåĪ°
    0.08
    åģļæ³ķ
    0.08
    è¿ĺæĺ¯éľĢè¦ģ
    0.07
    è¿Ļç§įåģļæ³ķ
    0.07
     Hilfs
    0.07
    otre
    0.07
    먹
    0.07
    åĬ©æĶ»
    0.07
    Activations Density 0.236%

    No Known Activations