© 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. 798
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    akens
    -0.23
    äºĨ好åĩł
    -0.21
    Χ
    -0.20
    .RightToLeft
    -0.20
    ŵ
    -0.19
    éĢīæĭ
    -0.19
    ><![
    -0.19
    ."&
    -0.19
    .cloudflare
    -0.19
    éĢĨåĬ¿
    -0.19
    POSITIVE LOGITS
    *>*
    0.26
    ]={↵
    0.21
    sap
    0.21
     MainAxisAlignment
    0.21
    olicited
    0.20
    :convert
    0.20
    ForMember
    0.20
    ultureInfo
    0.20
    aju
    0.20
    strtolower
    0.19
    Activations Density 0.708%

    No Known Activations