© 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. 2776
    Prev
    Next
    INDEX
    Explanations

    Summing up announcements

    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
    .OrderByDescending
    -0.28
    ();++
    -0.24
    addComponent
    -0.24
    ä¹łè¿ijå¹³æĢ»
    -0.24
     tatto
    -0.23
    ">ÃĹ</
    -0.23
     èĩªåĬ¨çĶŁæĪIJ
    -0.23
    IENTATION
    -0.23
    ä¹łè¿ij
    -0.23
     libertin
    -0.23
    POSITIVE LOGITS
     hex
    0.20
    estr
    0.19
     TO
    0.19
     Hex
    0.19
     اÙĦÙĪØŃ
    0.19
    æĹ©æľŁ
    0.19
     Top
    0.18
    ahn
    0.18
    aan
    0.18
    æĹ©çĤ¹
    0.18
    Activations Density 0.001%

    No Known Activations