© 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. 2233
    Prev
    Next
    INDEX
    Explanations

    text fragments

    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
    pson
    -0.33
    adoo
    -0.31
    ummings
    -0.30
    elight
    -0.29
    indow
    -0.28
    acades
    -0.27
    leck
    -0.27
    urrenc
    -0.26
    przed
    -0.26
    otland
    -0.26
    POSITIVE LOGITS
    ÐĿик
    0.25
    éģĽ
    0.23
     organisé
    0.23
    ä»ĭç»įä¸Ģä¸ĭ
    0.22
    çĭłæĬĵ
    0.21
    ca
    0.21
    è·ŁæĪij说
    0.21
    ç§ijçłĶéĻ¢
    0.20
     vbCrLf
    0.20
    çľ¼è¢ĭ
    0.20
    Activations Density 0.176%

    No Known Activations