© 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. 497
    Prev
    Next
    INDEX
    Explanations

    Q&A or code

    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
     piger
    -0.25
    intégr
    -0.25
    家éĥ½çŁ¥éģĵ
    -0.24
    <tag
    -0.22
    ionic
    -0.21
    BoxLayout
    -0.21
    çĤ¹å¤´
    -0.20
    /Dk
    -0.20
     Chr
    -0.20
    GBK
    -0.20
    POSITIVE LOGITS
     altercation
    0.20
    åĽ¢å§Ķ
    0.20
     XCT
    0.19
    ENCHMARK
    0.19
    _epi
    0.18
     afs
    0.18
     bytesRead
    0.18
    roup
    0.18
     acheter
    0.18
    ")!=
    0.18
    Activations Density 0.001%

    No Known Activations