© 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. 1936
    Prev
    Next
    INDEX
    Explanations

    varied specific contexts

    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
    illiseconds
    -0.24
    ;"><?
    -0.23
    å¾Īå¤ļçݩ家
    -0.23
    éĶĥ
    -0.23
    entiful
    -0.22
    rored
    -0.22
    (IService
    -0.22
    (strtolower
    -0.22
    ç³ĸå°¿
    -0.21
    ÑĦик
    -0.21
    POSITIVE LOGITS
    ,DB
    0.22
    -Feb
    0.21
    æĻĹ
    0.20
    criptor
    0.19
    ÙħÙĪÙĤع
    0.19
    'order
    0.19
    ÙħÙĪضÙĪع
    0.19
    '])?
    0.18
    ière
    0.18
    åı¯æĢľ
    0.18
    Activations Density 0.001%

    No Known Activations