© 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. 45983
    Prev
    Next
    INDEX
    Explanations

    code separators

    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
    üss
    -0.07
    ann
    -0.07
    ych
    -0.07
    oron
    -0.07
    reu
    -0.07
     Fiorent
    -0.07
    微信æī«çłģ
    -0.06
    æī³
    -0.06
    orie
    -0.06
     reass
    -0.06
    POSITIVE LOGITS
    EGIN
    0.08
     afs
    0.07
    stad
    0.07
    poste
    0.07
    缸åºĶ
    0.07
    âĹ¯
    0.07
    æ°ı
    0.07
    ibilities
    0.06
    _contents
    0.06
     Smithsonian
    0.06
    Activations Density 0.041%

    No Known Activations