© 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. 998
    Prev
    Next
    INDEX
    Explanations

    code structures

    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
    [opt
    -0.28
    [--
    -0.26
    oriously
    -0.26
    }_${
    -0.25
     adapté
    -0.24
    )./
    -0.23
     fkk
    -0.23
    /↵↵↵↵
    -0.23
    }.${
    -0.22
    ycin
    -0.22
    POSITIVE LOGITS
     deprecated
    0.20
     fray
    0.19
     ranger
    0.19
    ç±³å°Ķ
    0.18
    oce
    0.18
     humili
    0.18
    noinspection
    0.18
    åIJ¦åīĩ
    0.18
     Joi
    0.17
     scrollTop
    0.17
    Activations Density 2.653%

    No Known Activations