© 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. 45
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    éľ°
    -0.20
    è¯Į
    -0.20
    utzt
    -0.19
    ÑĮÑıн
    -0.19
    ().'/
    -0.19
    ÐĵÐŀ
    -0.18
    注æĺİåĩºå¤Ħ
    -0.18
    armor
    -0.18
    .webkit
    -0.18
    nemonic
    -0.18
    POSITIVE LOGITS
    âĸ·
    0.25
     "&#
    0.24
    :return
    0.23
    UIScreen
    0.23
     rencont
    0.22
    -strokes
    0.22
     libertine
    0.22
     Citation
    0.21
    =findViewById
    0.21
    INGTON
    0.20
    Activations Density 0.280%

    No Known Activations