© 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. 4182
    Prev
    Next
    INDEX
    Explanations

    size type passed

    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
    lean
    -0.08
     gren
    -0.08
     carn
    -0.07
     Roc
    -0.07
    034
    -0.06
     pand
    -0.06
     schwar
    -0.06
     sponsoring
    -0.06
    utes
    -0.06
     Bols
    -0.06
    POSITIVE LOGITS
     Ri
    0.10
    lij
    0.10
    otec
    0.10
    otherwise
    0.10
     otherwise
    0.10
    :');↵
    0.10
    Otherwise
    0.10
    owitz
    0.10
    nyder
    0.10
    ape
    0.09
    Activations Density 0.214%

    No Known Activations