© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4014
    Prev
    Next
    INDEX
    Explanations

    code and formatting

    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
    <main
    -0.23
    :".$
    -0.22
    à¸Ħม
    -0.20
    .getSeconds
    -0.19
    éĵħ
    -0.19
    ilogy
    -0.18
    ListComponent
    -0.18
    ,
    -0.18
    تØŃض
    -0.18
     ?>↵↵↵
    -0.18
    POSITIVE LOGITS
    edido
    0.24
    __;
    0.24
    å
    0.22
    -pocket
    0.21
     #+#
    0.20
    osexual
    0.20
    toa
    0.20
    ELLOW
    0.20
    .alibaba
    0.20
    ceipt
    0.19
    Activations Density 0.001%

    No Known Activations