© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3887
    Prev
    Next
    INDEX
    Explanations

    lessness and ity

    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
    .epam
    -0.23
    ÃĹ</
    -0.21
    piler
    -0.20
    nqu
    -0.20
    anst
    -0.20
    /*/
    -0.20
    -ln
    -0.20
     lokale
    -0.20
    möglich
    -0.20
    KeyType
    -0.19
    POSITIVE LOGITS
    /non
    0.58
    ä¸İåIJ¦
    0.53
     ÙĪغÙĬر
    0.40
    less
    0.38
    lessness
    0.30
    -less
    0.28
    ness
    0.28
    /not
    0.28
    å°ij
    0.24
    ity
    0.23
    Activations Density 1.097%

    No Known Activations