© 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. 39232
    Prev
    Next
    INDEX
    Explanations

    financial service terms

    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
    -0.08
    ersch
    -0.07
    agina
    -0.07
    nbsp
    -0.07
    Ìģ
    -0.07
     Uniti
    -0.06
    игÑĢа
    -0.06
    lite
    -0.06
    -toggler
    -0.06
    
    -0.06
    POSITIVE LOGITS
    è¦ģä¹Īæĺ¯
    0.08
    omini
    0.07
    ä½łä¸Ģ个
    0.07
    urada
    0.07
     миÑĢ
    0.07
    enticated
    0.06
    enser
    0.06
    apter
    0.06
    chnet
    0.06
    æ¯Ķåħ¶ä»ĸ
    0.06
    Activations Density 0.006%

    No Known Activations