© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 114
    Prev
    Next
    INDEX
    Explanations

    programming functions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OfWork
    -0.25
    .scalablytyped
    -0.24
    Uvs
    -0.24
    @show
    -0.23
    oriously
    -0.23
    .TODO
    -0.22
    @student
    -0.21
    #+
    -0.21
    ContentLoaded
    -0.21
    IColor
    -0.20
    POSITIVE LOGITS
    å¾Ĺå¾Ī好
    0.28
    _all
    0.26
    All
    0.25
    äºĨ好åĩł
    0.25
    äºĨåįĬ天
    0.23
    åĴĮå®ĮåĸĦ
    0.23
    å¾Ĺ太
    0.23
    潸
    0.22
    å¥
    0.21
    å¾Ĺ好
    0.21
    Activations Density 0.990%

    No Known Activations