© 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. 248
    Prev
    Next
    INDEX
    Explanations

    code and symbols

    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
     ofApp
    -0.26
     sucht
    -0.23
    çĭĻåĩ»
    -0.21
    \uD
    -0.20
     lac
    -0.20
    Ø£ÙĨØ´
    -0.20
    ëIJĺìĹĪ
    -0.19
    Í
    -0.19
     Bá
    -0.19
     onder
    -0.19
    POSITIVE LOGITS
     Ñģдела
    0.26
    ApiController
    0.26
     cerco
    0.25
    游æĪıéĩĮçļĦ
    0.25
    游æĪıå½ĵä¸Ń
    0.24
     "','
    0.24
    ”çļĦ
    0.24
    opportunitÃł
    0.23
     REUTERS
    0.23
    æĶ¯çº¿ä»»åĬ¡
    0.23
    Activations Density 0.494%

    No Known Activations