© 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. 49293
    Prev
    Next
    INDEX
    Explanations

    .gov websites

    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
    pered
    -0.08
    è¦ıç´Ħ
    -0.08
    å¤ļè°¢
    -0.08
    adel
    -0.07
     Goldberg
    -0.07
     Blvd
    -0.07
    汽车ç½ij
    -0.07
    èģĶåIJĪåĪĽå§ĭ人
    -0.07
    éĹ²
    -0.07
    Elite
    -0.07
    POSITIVE LOGITS
    .gov
    0.11
     guidance
    0.09
    ç»ĩ女
    0.08
    æĮĩåįĹ
    0.07
     Directorate
    0.07
     Guidance
    0.07
    GUID
    0.07
     visit
    0.07
    å¯ĵ
    0.07
    åľ¨äº¬
    0.07
    Activations Density 0.562%

    No Known Activations