© 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. 4311
    Prev
    Next
    INDEX
    Explanations

    contribute to

    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
    imum
    -0.09
    ities
    -0.08
    IMUM
    -0.08
    arness
    -0.08
    ä¹ĭæģĭ
    -0.08
    kest
    -0.08
    quee
    -0.08
    LIK
    -0.08
    zerű
    -0.07
    avais
    -0.07
    POSITIVE LOGITS
    ively
    0.11
    èī¯å¤ļ
    0.08
    åĪ°ä»ĸ
    0.08
    äºİä¸Ģ
    0.08
    欲滴
    0.07
    asikan
    0.07
    人åĪ°
    0.07
    ivate
    0.07
    utory
    0.07
    неÑģиÑĤе
    0.07
    Activations Density 0.034%

    No Known Activations