© 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. 588
    Prev
    Next
    INDEX
    Explanations

    articles

    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
    ç§ijæĬĢèĤ¡ä»½
    -0.23
     démarch
    -0.21
     effort
    -0.21
    ESCO
    -0.20
    ainment
    -0.20
    úsqueda
    -0.20
    çļĦåĬªåĬĽ
    -0.20
    -valu
    -0.20
    piler
    -0.20
    calar
    -0.20
    POSITIVE LOGITS
    ä¹ĭ称
    0.35
    Been
    0.24
     been
    0.24
    说èĩªå·±
    0.24
    åĬłæĮģ
    0.23
     capability
    0.23
     history
    0.23
     chance
    0.22
    çī¹çĤ¹
    0.22
    åı¯ä¾Ľ
    0.22
    Activations Density 2.889%

    No Known Activations