© 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. 50224
    Prev
    Next
    INDEX
    Explanations

    than

    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
    åħ¶ä¸ŃæľĢ
    -0.09
     everywhere
    -0.08
     anew
    -0.08
     newest
    -0.08
     latest
    -0.08
     new
    -0.07
    æľĢå¤ļçļĦ
    -0.07
     again
    -0.07
    åľ¨æľĢ
    -0.07
     оÑĩеÑĢедной
    -0.07
    POSITIVE LOGITS
    _than
    0.15
     than
    0.15
    than
    0.15
    -than
    0.14
     besides
    0.14
    Than
    0.14
     THAN
    0.13
     Than
    0.13
     niż
    0.11
     nữa
    0.11
    Activations Density 0.444%

    No Known Activations