© 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. 843
    Prev
    Next
    INDEX
    Explanations

    technical topics

    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
    resden
    -0.19
     démarch
    -0.19
    isFunction
    -0.19
     gode
    -0.18
    solete
    -0.18
     <!--[
    -0.18
    ichen
    -0.18
    apes
    -0.18
     burge
    -0.18
     airstrikes
    -0.17
    POSITIVE LOGITS
    ðŁ¤ĵ
    0.21
    alous
    0.21
    osit
    0.21
    venience
    0.20
    éĦľ
    0.20
    idUser
    0.19
    orElse
    0.19
    Subscribe
    0.19
    _nsec
    0.18
    aks
    0.18
    Activations Density 0.002%

    No Known Activations