© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3671
    Prev
    Next
    INDEX
    Explanations

    and or

    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
     FindObjectOfType
    -0.22
    UIColor
    -0.22
    :view
    -0.21
    esktop
    -0.20
    erguson
    -0.20
    ä¸Ģä½ĵåĮĸ
    -0.19
     Crow
    -0.19
    utations
    -0.19
    .ManyToMany
    -0.19
    batim
    -0.18
    POSITIVE LOGITS
    .simps
    0.23
    æ½ľåľ¨
    0.23
    ç»
    0.22
    裨
    0.21
    æĽ¾ç»ı
    0.21
    ðŁ¥ĩ
    0.21
    BuilderInterface
    0.21
    æĭŁ
    0.20
    两个维æĬ¤
    0.20
    åį³å°Ĩ
    0.20
    Activations Density 0.243%

    No Known Activations