© 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. 234
    Prev
    Next
    INDEX
    Explanations

    say digits

    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
    etur
    -0.24
    sist
    -0.23
    loomberg
    -0.22
    flate
    -0.21
    ilor
    -0.21
    ÃŃstico
    -0.20
    âį¨
    -0.20
    -au
    -0.20
     HtmlWebpackPlugin
    -0.20
    stile
    -0.19
    POSITIVE LOGITS
    ç½ijåıĭè¯Ħ论
    0.20
    ForMember
    0.19
    ']!='
    0.19
    ÑĪибка
    0.19
    å±Ĥåĩº
    0.19
     practition
    0.18
    ('').
    0.18
     fkk
    0.18
    åħ¸
    0.18
    ëŀ©
    0.18
    Activations Density 0.153%

    No Known Activations