© 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. 547
    Prev
    Next
    INDEX
    Explanations

    amino acid residue

    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
    -scrollbar
    -0.23
    ä½ľåĿĬ
    -0.23
    _argv
    -0.23
     daily
    -0.21
     Baghd
    -0.20
    -divider
    -0.20
     grated
    -0.20
    xCD
    -0.20
    -initialized
    -0.20
    assertSame
    -0.19
    POSITIVE LOGITS
    çŀŁ
    0.28
    ("'"
    0.28
    建档ç«ĭ
    0.27
    (*)(
    0.25
    :host
    0.25
    âļĹ
    0.25
    ç»ĵæŀĦ
    0.24
    ,Yes
    0.24
    صÙĨد
    0.24
    structuring
    0.23
    Activations Density 2.405%

    No Known Activations