© 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. 2440
    Prev
    Next
    INDEX
    Explanations

    technical or specific words

    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
     G
    -0.24
    ä¸įåıĺ
    -0.22
    -0.20
     R
    -0.20
    çIJĨ
    -0.20
     Corner
    -0.19
    /
    -0.19
    er
    -0.19
    :
    -0.19
     (
    -0.18
    POSITIVE LOGITS
    çĽijåIJ¬é¡µéĿ¢
    0.26
    alian
    0.26
    rawid
    0.24
    abbix
    0.24
    -FIRST
    0.24
    ?"↵↵↵↵
    0.24
    çĪ±å¥ĩ
    0.24
     Ä°nternet
    0.23
    byter
    0.23
    matchCondition
    0.23
    Activations Density 0.002%

    No Known Activations