© 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. 2335
    Prev
    Next
    INDEX
    Explanations

    specific entities and text

    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
    abbo
    -0.24
    BOSE
    -0.23
     '..',
    -0.23
    kaar
    -0.22
    oriously
    -0.22
    á»ĭch
    -0.21
     INCLUDED
    -0.20
    ëĮĦ
    -0.20
    å³»
    -0.20
    éĶĴ
    -0.20
    POSITIVE LOGITS
     ×Ķ×ķ×ĵ
    0.24
    åĪ©çĶ¨æĤ¨çļĦ
    0.24
    اÙĦØ·
    0.23
    å¤įå·¥å¤į
    0.23
    _flashdata
    0.21
    dehy
    0.21
     umo
    0.20
    æľīçļĦçݩ家
    0.20
    åı¶ä¿®
    0.20
    æĢİ
    0.20
    Activations Density 0.001%

    No Known Activations