© 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. 1848
    Prev
    Next
    INDEX
    Explanations

    return

    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
    благо
    -0.20
    ÐŁÐµÑĤеÑĢ
    -0.20
    奢ä¾Ī
    -0.20
    å¤įå·¥å¤į
    -0.20
    çĺIJ
    -0.19
    /Register
    -0.19
    .imageUrl
    -0.18
    ãĥµ
    -0.18
    å¹´ä¹ĭä¹ħ
    -0.18
    });↵↵↵↵
    -0.18
    POSITIVE LOGITS
    ç»ĵæŀľ
    0.25
    ********************************************************************************
    0.24
     sovere
    0.24
    uche
    0.23
    riger
    0.22
    Į¨
    0.20
    upertino
    0.20
     success
    0.20
     suk
    0.20
    -done
    0.19
    Activations Density 0.620%

    No Known Activations