© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 1536
    Prev
    Next
    INDEX
    Explanations

    ert

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nek
    -0.09
    alette
    -0.09
    flt
    -0.09
    ROWS
    -0.08
    edor
    -0.08
    ifer
    -0.08
    bring
    -0.08
    ·¨
    -0.08
    ulus
    -0.08
     Kenn
    -0.08
    POSITIVE LOGITS
    at
    0.10
    inne
    0.09
     Tess
    0.09
    bbe
    0.09
    m
    0.09
     Maurice
    0.09
    rish
    0.09
    asca
    0.08
    cip
    0.08
    r
    0.08
    Activations Density 1.799%

    No Known Activations