© 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. 32078
    Prev
    Next
    INDEX
    Explanations

    list.getChildAt

    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
    ame
    -0.06
     com
    -0.06
     serv
    -0.06
    -0.06
     /
    -0.05
    éħįæĪ´
    -0.05
     def
    -0.05
     |
    -0.05
    ł
    -0.05
    rame
    -0.05
    POSITIVE LOGITS
    ä»»ä½ķåħ¶ä»ĸ
    0.12
     lainnya
    0.10
    ãģĿãģĨãģ§
    0.10
     pula
    0.10
    >:</
    0.09
     sonstige
    0.09
     sonst
    0.08
    .TryParse
    0.08
     –**
    0.08
    ãģ¾ãģĦ
    0.08
    Activations Density 0.192%

    No Known Activations