© 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. 2460
    Prev
    Next
    INDEX
    Explanations

    Information exchange

    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
    ?>>
    -0.23
    rientation
    -0.22
    .bumptech
    -0.21
    зван
    -0.20
    ltre
    -0.20
    ccoli
    -0.20
    تغÙĬ
    -0.20
    udit
    -0.19
     reluct
    -0.19
     leo
    -0.19
    POSITIVE LOGITS
    Æ°á»Ľng
    0.20
    ARG
    0.19
     TouchableOpacity
    0.19
    è®®
    0.19
    ongyang
    0.18
    itational
    0.18
     Jackets
    0.18
    åĶ¤
    0.18
    AssignableFrom
    0.18
    纰
    0.18
    Activations Density 0.008%

    No Known Activations