© 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. 213
    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
    çŀŁ
    -0.23
    /Dk
    -0.22
    bió
    -0.20
    ylum
    -0.20
     actionTypes
    -0.20
    hausen
    -0.19
    :maj
    -0.19
    kus
    -0.19
    ç¡ļ
    -0.19
    (DWORD
    -0.19
    POSITIVE LOGITS
    .radians
    0.26
     Bedrooms
    0.25
    äºĨ好åĩł
    0.22
     cerco
    0.21
    çĻ«çĹ«çĹħ
    0.21
     çĶŁåij½åij¨æľŁ
    0.21
    ï¼ģ",
    0.20
     âĵĺ
    0.20
    ad
    0.20
    _UUID
    0.20
    Activations Density 0.272%

    No Known Activations