© 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. 12177
    Prev
    Next
    INDEX
    Explanations

    factual basis for decisions

    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
     atras
    -0.07
    boro
    -0.07
    occa
    -0.07
    ä¿Ŀåį«
    -0.07
    Rep
    -0.07
     Seguro
    -0.06
     menuntut
    -0.06
    ekat
    -0.06
    æĸ°éĹ»ä¼łæĴŃ
    -0.06
    åį«å£«
    -0.06
    POSITIVE LOGITS
     decision
    0.09
    Decision
    0.08
     Decision
    0.08
    åıĸèĪį
    0.08
    è¯Ħ
    0.08
    é©Ń
    0.08
    decision
    0.07
    éĩĩä¿¡
    0.07
    èĩ
    0.07
     decisions
    0.07
    Activations Density 0.018%

    No Known Activations