© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61936
    Prev
    Next
    INDEX
    Explanations

    states or null values

    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
    enk
    -0.07
    欢
    -0.07
    биÑĤ
    -0.07
    åĨ¥
    -0.07
    ourt
    -0.07
    缴æİ¥æĪĸéĹ´æİ¥
    -0.07
    enth
    -0.06
    leven
    -0.06
     Turqu
    -0.06
    бÑĥдÑĮ
    -0.06
    POSITIVE LOGITS
    èĢĮéĿŀ
    0.15
    èĢĮä¸įæĺ¯
    0.15
     rather
    0.13
     plutôt
    0.13
    rather
    0.12
     statt
    0.12
     instead
    0.11
    instead
    0.10
     piuttosto
    0.10
     Rather
    0.10
    Activations Density 0.031%

    No Known Activations