© 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. 3220
    Prev
    Next
    INDEX
    Explanations

    that explains why

    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
    æĪij
    -0.10
     I
    -0.09
     Stranger
    -0.08
     my
    -0.08
    %!
    -0.08
     meiner
    -0.08
    our
    -0.08
    ponce
    -0.08
     valide
    -0.08
     Noon
    -0.08
    POSITIVE LOGITS
    aket
    0.09
     mattered
    0.09
    007
    0.09
    cen
    0.08
    ses
    0.08
     Klein
    0.08
     ect
    0.08
     hic
    0.08
    amble
    0.08
    OW
    0.08
    Activations Density 0.256%

    No Known Activations