© 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. 2653
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

    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
     Gates
    -0.22
    çĭ
    -0.20
    ĵĺ
    -0.20
    +offset
    -0.20
    getHeight
    -0.20
     Kardash
    -0.20
    å¼Ł
    -0.20
    },{↵
    -0.19
    /GPL
    -0.19
     Osw
    -0.18
    POSITIVE LOGITS
    楯
    0.22
     rall
    0.21
    .apiUrl
    0.21
    .getBounds
    0.20
    Spell
    0.20
    (mysqli
    0.19
    Verdana
    0.19
    伶
    0.19
    InputChange
    0.19
    åµ
    0.19
    Activations Density 0.001%

    No Known Activations