© 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. 2874
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    BOSE
    -0.21
    代
    -0.20
     buflen
    -0.20
    räg
    -0.19
    EPROM
    -0.19
    _MODAL
    -0.19
    è¡Ħ
    -0.19
    ().'/
    -0.19
    -INF
    -0.18
    xAB
    -0.18
    POSITIVE LOGITS
    exampleModal
    0.22
    rale
    0.21
    mé
    0.21
    arnation
    0.20
    estyle
    0.20
    .Once
    0.20
    indre
    0.20
    .IsNullOr
    0.20
    )(((
    0.20
    frei
    0.20
    Activations Density 0.000%

    No Known Activations