© 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. 44922
    Prev
    Next
    INDEX
    Explanations

    to clarify or confirm

    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
     Tatsache
    -0.08
    sic
    -0.08
    çļĦéĤ£æł·
    -0.07
    èµŀè¿ĩ
    -0.07
    recken
    -0.07
     magas
    -0.07
    transport
    -0.07
    ìłľíķľ
    -0.07
    untime
    -0.07
    ç»ı
    -0.07
    POSITIVE LOGITS
     conclus
    0.08
    确认
    0.07
    çIJĨæ¸ħ
    0.07
    ัà¸Ī
    0.07
    確èªį
    0.07
    åĪĨä¹ĭ
    0.07
     понÑıÑĤÑĮ
    0.07
    mise
    0.07
     confirm
    0.07
     elucid
    0.07
    Activations Density 0.057%

    No Known Activations