© 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. 3289
    Prev
    Next
    INDEX
    Explanations

    stand

    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
    leanor
    -0.28
    -Methods
    -0.24
    lijah
    -0.24
    berra
    -0.24
    )./
    -0.23
    buat
    -0.23
    çŀŁ
    -0.23
    astle
    -0.23
    bish
    -0.23
    oproject
    -0.23
    POSITIVE LOGITS
     stand
    0.29
    åĢĻ
    0.27
     stands
    0.27
    ç«ĭ
    0.24
    stand
    0.23
     stood
    0.23
     stance
    0.23
     standing
    0.22
    -standing
    0.22
     position
    0.22
    Activations Density 0.142%

    No Known Activations