© 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. 15
    Prev
    Next
    INDEX
    Explanations

    such

    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
     (~(
    -0.24
    ,'#
    -0.24
    :'.$
    -0.23
    =:
    -0.23
    xAC
    -0.21
    },{↵
    -0.21
    .UseVisualStyleBackColor
    -0.21
    صÙĨد
    -0.20
     potrÃł
    -0.20
     exercitation
    -0.20
    POSITIVE LOGITS
    æ¯Ķå¦Ĥ
    1.09
    诸å¦Ĥ
    1.03
    ä¾ĭå¦Ĥ
    0.97
    åĮħæĭ¬
    0.86
     such
    0.85
    èѬå¦Ĥ
    0.79
     including
    0.78
    å¦Ĥ
    0.77
    æ¯Ķå¦Ĥ说
    0.77
    such
    0.73
    Activations Density 5.855%

    No Known Activations