© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 28694
    Prev
    Next
    INDEX
    Explanations

    when or for

    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
    aeda
    -0.08
    å±±éĩĮ
    -0.08
    onge
    -0.07
    ickets
    -0.07
    zwi
    -0.07
    stal
    -0.07
    Locator
    -0.07
    anka
    -0.07
    amme
    -0.07
    ä¸Ĭ个æľĪ
    -0.07
    POSITIVE LOGITS
     when
    0.11
     across
    0.09
     khi
    0.08
    edik
    0.08
    å½ĵ
    0.08
    when
    0.08
     regardless
    0.07
    обо
    0.07
     after
    0.07
     for
    0.07
    Activations Density 0.415%

    No Known Activations