© 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. 29798
    Prev
    Next
    INDEX
    Explanations

    sheet applications

    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
     Burgess
    -0.08
    ׼×ķ׾
    -0.08
    веÑĤ
    -0.08
    _rev
    -0.07
    åıijè¯ģ
    -0.07
    å¦Ĥæ½®
    -0.07
    °
    -0.07
    åIJĪæł¼çļĦ
    -0.07
     нали
    -0.07
     rev
    -0.07
    POSITIVE LOGITS
    (((
    0.07
    kah
    0.07
    åĨµ
    0.07
    peak
    0.07
    (-(
    0.07
    ẻo
    0.06
    finalize
    0.06
    ìĵ°
    0.06
    ((
    0.06
    .reader
    0.06
    Activations Density 0.032%

    No Known Activations