© 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. 3550
    Prev
    Next
    INDEX
    Explanations

    If

    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
    land
    -0.10
    ISCO
    -0.09
     introdu
    -0.09
     therefore
    -0.09
    _spacing
    -0.09
    ergy
    -0.09
    Hover
    -0.09
    -ret
    -0.09
    (Source
    -0.08
     Courtney
    -0.08
    POSITIVE LOGITS
     Suff
    0.13
    yar
    0.09
     suffice
    0.08
    kor
    0.08
     foil
    0.08
    faq
    0.08
     Brief
    0.07
    yah
    0.07
     prefixed
    0.07
     note
    0.07
    Activations Density 0.349%

    No Known Activations