© 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. 31352
    Prev
    Next
    INDEX
    Explanations

    contrast or comparison

    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
    ابع
    -0.07
    OrCreate
    -0.07
    estes
    -0.07
    poon
    -0.07
    ofs
    -0.06
    PM
    -0.06
     lắm
    -0.06
    à¸ŀล
    -0.06
    以åıĬ缸åħ³
    -0.06
     Kop
    -0.06
    POSITIVE LOGITS
     whereas
    0.18
     Whereas
    0.17
     ë°ĺë©´
    0.16
    èĢĮ
    0.15
     versus
    0.13
    缸æ¯Ķä¹ĭä¸ĭ
    0.13
    èĢĮåħ¶ä»ĸ
    0.13
    åıįè§Ĥ
    0.13
     tandis
    0.13
     Sedangkan
    0.12
    Activations Density 0.116%

    No Known Activations