© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2708
    Prev
    Next
    INDEX
    Explanations

    starting a process

    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
    QDebug
    -0.23
    afür
    -0.23
    å©ķ
    -0.23
     IonicPage
    -0.22
    游æĪıæĬĢå·§
    -0.21
    @update
    -0.20
    iddles
    -0.20
    herits
    -0.20
    çĴIJ
    -0.20
    oubted
    -0.20
    POSITIVE LOGITS
     process
    0.31
     series
    0.30
    ä¹ĭæĹħ
    0.30
     campaign
    0.30
    å¾ģç¨ĭ
    0.29
    è¿Ľç¨ĭ
    0.28
    series
    0.27
    æĶ»åĬ¿
    0.26
     journey
    0.26
     efforts
    0.26
    Activations Density 0.755%

    No Known Activations