© 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. 3594
    Prev
    Next
    INDEX
    Explanations

    financial and technical terms

    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
    коло
    -0.23
    airobi
    -0.22
     potrÃł
    -0.22
    /original
    -0.21
    TTY
    -0.20
    æĥ«
    -0.20
    noinspection
    -0.20
    ＾＾
    -0.19
    /loading
    -0.19
    Ä°R
    -0.19
    POSITIVE LOGITS
     valueForKey
    0.22
    eah
    0.21
    atsby
    0.20
    ecycle
    0.20
    eel
    0.20
    ossal
    0.19
    Disappear
    0.19
    yne
    0.19
    apg
    0.19
    inea
    0.19
    Activations Density 0.001%

    No Known Activations