© 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. 20848
    Prev
    Next
    INDEX
    Explanations

    request-related terms

    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
    arity
    -0.09
    licity
    -0.08
    thest
    -0.08
     بÙĨدÛĮ
    -0.08
    anness
    -0.08
    éļĪ
    -0.08
    лков
    -0.08
    utine
    -0.08
    itó
    -0.08
    arness
    -0.08
    POSITIVE LOGITS
    AnimationFrame
    0.11
    er
    0.10
    eer
    0.10
    ï¾ŀ
    0.08
    /response
    0.08
    ful
    0.08
    orious
    0.08
    ably
    0.08
    ur
    0.08
    ive
    0.08
    Activations Density 0.036%

    No Known Activations