© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2772
    Prev
    Next
    INDEX
    Explanations

    technical identifiers

    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
    æĸĵ
    -0.22
    :"",
    -0.22
     disp
    -0.21
    :///
    -0.20
    leftright
    -0.20
    iscard
    -0.19
    ()?>
    -0.19
    riends
    -0.19
    jsx
    -0.18
    disp
    -0.18
    POSITIVE LOGITS
    /stretch
    0.23
     cellFor
    0.23
    bservice
    0.21
     honda
    0.21
     Raider
    0.20
    _RA
    0.20
    天åłĤ
    0.20
    swick
    0.19
     nonatomic
    0.19
    ported
    0.19
    Activations Density 0.002%

    No Known Activations