© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4001
    Prev
    Next
    INDEX
    Explanations

    context-specific identifiers

    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
    eworthy
    -0.22
    еÑģÑĤво
    -0.20
    ceries
    -0.20
    ategorias
    -0.20
    婳
    -0.20
    æ´¸
    -0.20
    ç¬Ī
    -0.19
    ibal
    -0.19
     culpa
    -0.19
    /examples
    -0.18
    POSITIVE LOGITS
    _INCLUDED
    0.22
    nyder
    0.21
    grÃ¶ÃŁe
    0.20
    âĦī
    0.20
     Metodo
    0.19
    hardt
    0.19
    Wil
    0.19
    .elementAt
    0.18
    ackson
    0.18
    _LOGGER
    0.18
    Activations Density 0.001%

    No Known Activations