© 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. 22861
    Prev
    Next
    INDEX
    Explanations

    equal length or same length

    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
    лд
    -0.07
    auer
    -0.07
    à¸Ŀ
    -0.07
    ulk
    -0.07
    ressive
    -0.07
    Combo
    -0.07
    æĿ¥å¾ĹåıĬ
    -0.07
    .rf
    -0.07
    (--
    -0.07
     Musa
    -0.07
    POSITIVE LOGITS
    缸çŃī
    0.16
     equal
    0.15
     Equal
    0.15
    对称
    0.15
    equal
    0.14
     symmetry
    0.14
     unequal
    0.14
     equality
    0.14
    Equal
    0.13
     Equality
    0.13
    Activations Density 0.031%

    No Known Activations