© 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. 851
    Prev
    Next
    INDEX
    Explanations

    as is basis

    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
     (![
    -0.24
    ç»´å¥ĩ
    -0.21
    requete
    -0.20
    iomanip
    -0.20
    'icon
    -0.20
    oggler
    -0.19
    ëĶ°
    -0.19
    STRUCTIONS
    -0.18
    la
    -0.18
    cassert
    -0.18
    POSITIVE LOGITS
    ,application
    0.26
    icens
    0.22
    rray
    0.22
    :numel
    0.22
     without
    0.22
    ",__
    0.21
    ocaly
    0.21
    sexo
    0.20
     volunte
    0.20
     WITHOUT
    0.20
    Activations Density 0.441%

    No Known Activations