© 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. 63609
    Prev
    Next
    INDEX
    Explanations

    separating characters and 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
    豪
    -0.07
     pied
    -0.07
     ser
    -0.07
    ingg
    -0.06
    ió
    -0.06
    ä¹ĭåĪĹ
    -0.06
     increment
    -0.06
     collectively
    -0.06
    vern
    -0.06
    ulia
    -0.06
    POSITIVE LOGITS
    -separated
    0.13
    éļĶå¼Ģ
    0.12
     separating
    0.11
    åĪĨéļĶ
    0.11
     separates
    0.10
    _separator
    0.10
    _SEPARATOR
    0.10
     بÙĬÙĨÙĩÙħا
    0.10
     Separator
    0.10
     Separ
    0.10
    Activations Density 0.046%

    No Known Activations