© 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. 22420
    Prev
    Next
    INDEX
    Explanations

    arc or arcs

    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
    à¸Ĺà¹Į
    -0.09
    itz
    -0.07
    tered
    -0.07
    cing
    -0.07
    zers
    -0.07
    waard
    -0.07
    ChildIndex
    -0.07
    -know
    -0.07
    áĢ·
    -0.07
    egers
    -0.07
    POSITIVE LOGITS
    uate
    0.10
    wise
    0.09
    age
    0.09
    itecture
    0.08
    ént
    0.08
    åºĩ
    0.08
    way
    0.08
    ophone
    0.08
     wise
    0.08
    icult
    0.07
    Activations Density 0.010%

    No Known Activations