© 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. 3914
    Prev
    Next
    INDEX
    Explanations

    technical miscellaneous

    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
    }_${
    -0.28
    "),"
    -0.23
    .ToUpper
    -0.22
    "path
    -0.22
    }-${
    -0.22
    个çĻ¾åĪĨ
    -0.22
    ä¼IJ
    -0.22
    :;"
    -0.21
    .jet
    -0.20
    ê
    -0.20
    POSITIVE LOGITS
    berra
    0.22
    inda
    0.20
     Desired
    0.20
    æĪijçĪ±ä½ł
    0.19
    -bel
    0.19
     Recommend
    0.18
     unins
    0.18
    ÙĥÙĪÙĥ
    0.18
    为é¦ĸçļĦ
    0.18
    .deepEqual
    0.18
    Activations Density 0.001%

    No Known Activations