© 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. 2215
    Prev
    Next
    INDEX
    Explanations

    code or technical terms

    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
     diseñador
    -0.19
    éĩį伤
    -0.19
    å¾ĹçĽĬ
    -0.19
     actionTypes
    -0.19
    ï¹Ĺ
    -0.18
    UGHT
    -0.18
    ackbar
    -0.18
    rib
    -0.18
    em
    -0.18
    æīĭèħķ
    -0.18
    POSITIVE LOGITS
    >Nama
    0.21
    ();?>
    0.20
    &)↵
    0.20
    &);↵↵
    0.20
    &);↵
    0.20
    PushMatrix
    0.19
     rep
    0.19
    æĵį
    0.18
    Ä©
    0.18
    <translation
    0.18
    Activations Density 0.001%

    No Known Activations