© 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. 1598
    Prev
    Next
    INDEX
    Explanations

    family or names

    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
    ridden
    -0.23
    #aa
    -0.23
    åİĨåı²æĸ°
    -0.23
    ecided
    -0.22
    ispens
    -0.21
    >());↵↵
    -0.21
    âĨµ
    -0.20
     tantra
    -0.20
    pecific
    -0.20
     hữu
    -0.20
    POSITIVE LOGITS
    ian
    0.29
    æ°ı
    0.28
     Family
    0.28
    çŃī人
    0.27
     Brothers
    0.24
     family
    0.24
    alborg
    0.24
    's
    0.24
    abilia
    0.24
     et
    0.23
    Activations Density 2.036%

    No Known Activations