© 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. 126
    Prev
    Next
    INDEX
    Explanations

    code and technical

    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
    asurer
    -0.23
    %X
    -0.22
    ].'
    -0.22
    пÑģи
    -0.22
    ﹩
    -0.21
    miÅŁ
    -0.21
    oltip
    -0.21
    égor
    -0.21
    à¦Ī
    -0.20
    bild
    -0.20
    POSITIVE LOGITS
     még
    0.23
    ÑĤели
    0.20
     sok
    0.20
     kad
    0.20
    缨
    0.19
     sag
    0.19
     tas
    0.19
     Premiership
    0.18
     masturbating
    0.18
     vej
    0.18
    Activations Density 0.001%

    No Known Activations