© 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. 2500
    Prev
    Next
    INDEX
    Explanations

    Loss and reflection

    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
     libertin
    -0.23
     repmat
    -0.22
     pij
    -0.20
     typical
    -0.19
    稽
    -0.19
    æī¾ä¸ª
    -0.19
    \Category
    -0.19
     experiences
    -0.19
    æķ°çĻ¾
    -0.19
    ä½Ĩåį´
    -0.18
    POSITIVE LOGITS
    æľĭåıĭ们对
    0.27
    æį¯
    0.25
     bénéficie
    0.25
    åĹIJ
    0.24
    olson
    0.24
    ';";↵
    0.24
    åļ¯
    0.23
    )&&
    0.23
    }}],↵
    0.23
    æļĮ
    0.22
    Activations Density 0.397%

    No Known Activations