© 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. 221
    Prev
    Next
    INDEX
    Explanations

    plural nouns

    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
     itself
    -0.47
    å®ĥçļĦ
    -0.34
     иÑģпÑĭÑĤа
    -0.31
     Its
    -0.29
    ä¹Łæĺ¯ä¸Ģ个
    -0.28
    åĽłä¸ºå®ĥ
    -0.28
    Its
    -0.28
    nyder
    -0.28
     коÑĤоÑĢое
    -0.27
     its
    -0.27
    POSITIVE LOGITS
     themselves
    0.70
     коÑĤоÑĢÑĭе
    0.49
     are
    0.42
    å®ĥ们
    0.41
    _are
    0.38
     ones
    0.37
    ä¹Łéĥ½
    0.35
    ä¸Ģ个个
    0.34
     were
    0.33
    éĥ½å¾Ī
    0.33
    Activations Density 9.748%

    No Known Activations