© 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. 28705
    Prev
    Next
    INDEX
    Explanations

    separating or segregating

    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
    缴æİ¥æĪĸ
    -0.08
    chw
    -0.08
    å¢
    -0.08
    ább
    -0.08
    acci
    -0.07
    ä¸įæŃ»
    -0.07
    inkan
    -0.07
    ä¸įéĻIJäºİ
    -0.07
    IDD
    -0.06
    akis
    -0.06
    POSITIVE LOGITS
    åĪĨå·¥
    0.15
    åĪĨ离
    0.14
     separation
    0.13
     separating
    0.13
    åIJĦåı¸
    0.12
    åĪĨå¼Ģ
    0.12
     separates
    0.12
     segreg
    0.12
    åĪĨåĩº
    0.11
    åĪĨéħį
    0.11
    Activations Density 0.252%

    No Known Activations