© 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. 3922
    Prev
    Next
    INDEX
    Explanations

    Dates or identifiers

    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
    volución
    -0.29
    pedia
    -0.26
    volução
    -0.26
    ecast
    -0.26
    byss
    -0.26
    ampie
    -0.26
    >({
    -0.25
    ])))
    -0.24
    )./
    -0.24
    linky
    -0.23
    POSITIVE LOGITS
     Decompiled
    0.24
    опÑĢеделен
    0.22
    entiful
    0.20
     robust
    0.20
    ä¸įå¤ļ
    0.19
     sıkıntı
    0.19
    è¶ĬæĿ¥è¶Ĭé«ĺ
    0.19
    _namespace
    0.18
    ä»İæł¹æľ¬
    0.18
    éŨ
    0.18
    Activations Density 0.001%

    No Known Activations