© 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. 2879
    Prev
    Next
    INDEX
    Explanations

    say "to"

    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
    MMdd
    -0.27
     activeClassName
    -0.22
     //č↵č↵
    -0.21
     ÑģенÑĤ
    -0.21
     dikke
    -0.21
    ForObject
    -0.21
    è´³
    -0.21
    BOSE
    -0.20
    räg
    -0.20
    .updateDynamic
    -0.20
    POSITIVE LOGITS
    åĪ°
    0.52
     to
    0.47
    èĩ³
    0.46
     unto
    0.36
     onto
    0.35
     Ø¥ÙĦÙī
    0.35
    èĩ³ä¸Ĭ
    0.34
    ToFile
    0.34
    _to
    0.32
    to
    0.32
    Activations Density 0.748%

    No Known Activations