© 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. 19696
    Prev
    Next
    INDEX
    Explanations

    uniquely determined or defined

    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
    illac
    -0.08
    åħ¼
    -0.08
    éĹ´æŃĩ
    -0.08
    égor
    -0.08
    ×ŀ×ķ×ĵ
    -0.07
    abaj
    -0.07
    avera
    -0.07
    ehl
    -0.07
    اش
    -0.07
    _fault
    -0.07
    POSITIVE LOGITS
     uniquely
    0.13
     unique
    0.10
     fixing
    0.09
    ç¡®å®ļäºĨ
    0.09
     specifying
    0.09
     Unique
    0.09
     uniqueness
    0.09
    Unique
    0.09
    å®ļäºĨ
    0.08
     однознаÑĩно
    0.08
    Activations Density 0.007%

    No Known Activations