© 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. 8971
    Prev
    Next
    INDEX
    Explanations

    legal document sections

    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
    odin
    -0.08
    ÂŃtion
    -0.08
    aim
    -0.08
    nage
    -0.08
    สà¸Ļà¸Ńà¸ĩ
    -0.08
    nal
    -0.08
    enticate
    -0.07
    è¦ģä¸į
    -0.07
    ÂŃs
    -0.07
    osal
    -0.07
    POSITIVE LOGITS
    र
    0.08
    Ùĩر
    0.08
    ↵
    0.08
    izing
    0.07
    il
    0.07
    åĮĸå¤ĦçIJĨ
    0.06
    ÑĪов
    0.06
    ìĸ´ëĤľ
    0.06
    ãģĦãĤĭ
    0.06
    err
    0.06
    Activations Density 0.933%

    No Known Activations