© 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. 21640
    Prev
    Next
    INDEX
    Explanations

    part / component / partner

    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
    ebo
    -0.08
    argins
    -0.08
    wok
    -0.08
    åĨħå¤ĸ
    -0.07
    ä¸ī代
    -0.07
    agh
    -0.07
    (Point
    -0.07
    isses
    -0.07
     SOUR
    -0.07
    .community
    -0.07
    POSITIVE LOGITS
     part
    0.13
     paired
    0.12
     counterpart
    0.11
     partner
    0.11
     alongside
    0.10
    éħįåIJĪ
    0.10
     companion
    0.10
    à¹Ģà¸Ľà¹ĩà¸Ļสà¹Īวà¸Ļ
    0.10
     component
    0.09
     partnering
    0.09
    Activations Density 0.259%

    No Known Activations