© 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. 2589
    Prev
    Next
    INDEX
    Explanations

    technical terms and names

    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
    è¿Ļä¸ªåľ°åĽ¾
    -0.28
    OffsetTable
    -0.23
    "is
    -0.21
     safeg
    -0.20
    éĶĽ
    -0.20
    .Quad
    -0.20
     Toastr
    -0.20
     erg
    -0.20
    sher
    -0.19
    .invoke
    -0.19
    POSITIVE LOGITS
    ']=="
    0.24
     Padres
    0.20
    ucson
    0.20
    opportunitÃł
    0.20
    èĭ±æł¼
    0.20
    vette
    0.19
    ']!='
    0.19
     Reform
    0.19
    å½¼
    0.19
     oct
    0.19
    Activations Density 0.001%

    No Known Activations