© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 686
    Prev
    Next
    INDEX
    Explanations

    vice versa, compared

    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
    åŀ§
    -0.25
    ä¸ĭéĿ¢å°ıç¼ĸ
    -0.24
     RoundedRectangle
    -0.21
    æį¢åı¥è¯Ŀ
    -0.20
    _APB
    -0.20
    prech
    -0.20
     *)((
    -0.19
    "log
    -0.19
    ËĬ
    -0.19
    .DAY
    -0.19
    POSITIVE LOGITS
    _HERSHEY
    0.26
    quete
    0.23
    ppard
    0.23
    ecure
    0.21
    ฯ
    0.20
    eparator
    0.20
    rvine
    0.20
    asurer
    0.19
    /stdc
    0.19
    0.19
    Activations Density 5.102%

    No Known Activations