© 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. 65311
    Prev
    Next
    INDEX
    Explanations

    code/math variable suffixes

    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
    çªŁ
    -0.07
    acci
    -0.07
    аниÑĨ
    -0.07
    ixer
    -0.07
     kia
    -0.07
     Stap
    -0.07
    ারণ
    -0.07
    åı«
    -0.06
    åĴĮæŶéĹ´
    -0.06
    Ùħر
    -0.06
    POSITIVE LOGITS
    others
    0.09
     others
    0.08
    itch
    0.08
    eya
    0.07
    Ŀ
    0.07
    ewel
    0.07
    è´
    0.07
     Others
    0.07
    orning
    0.07
    eté
    0.07
    Activations Density 0.008%

    No Known Activations