© 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. 95
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

    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
     regenerated
    -0.25
    posição
    -0.22
    åĨįçĶŁ
    -0.22
    ç½
    -0.21
    ",__
    -0.20
    Salvar
    -0.20
    acists
    -0.20
     hookers
    -0.19
     regeneration
    -0.19
    reur
    -0.18
    POSITIVE LOGITS
    !!");↵
    0.24
    æ¿Ģ
    0.23
    åİĦ
    0.20
    ucson
    0.20
    èĥģ
    0.20
    .textView
    0.19
    criptors
    0.19
    æªĦ
    0.18
    frica
    0.18
     CircularProgress
    0.18
    Activations Density 0.010%

    No Known Activations