© 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. 1657
    Prev
    Next
    INDEX
    Explanations

    go

    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
    forgettable
    -0.22
     vej
    -0.22
    èµ°åĩºæĿ¥
    -0.21
    åĽ½éĻħåľ¨çº¿
    -0.21
    个交æĺĵ
    -0.21
    ippines
    -0.20
    讧
    -0.20
    noinspection
    -0.19
    ver
    -0.19
    not
    -0.19
    POSITIVE LOGITS
    (Have
    0.26
    UGE
    0.22
    enarios
    0.21
    %X
    0.21
    verständlich
    0.21
    /fwlink
    0.20
    +-+-
    0.20
    qrst
    0.20
    (<?
    0.20
    oundingBox
    0.20
    Activations Density 0.518%

    No Known Activations