© 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. 24918
    Prev
    Next
    INDEX
    Explanations

    flat, special, uniform, white

    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
    IVI
    -0.08
     Crown
    -0.07
     Lonely
    -0.07
    cant
    -0.07
    ICAS
    -0.07
    itar
    -0.07
    Ùĩب
    -0.07
    ellone
    -0.07
    ponsible
    -0.07
     narrower
    -0.07
    POSITIVE LOGITS
     Flat
    0.08
    éĽ
    0.07
    缴
    0.07
     Explicit
    0.07
    Flat
    0.07
    bl
    0.07
    ä¸ĢåĪĩçļĦ
    0.07
    åºķåŃIJ
    0.07
    å¹³
    0.07
    Explicit
    0.07
    Activations Density 0.006%

    No Known Activations