© 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. 58565
    Prev
    Next
    INDEX
    Explanations

    ISBN, ISSN, postcode, car brands, names

    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
    ingen
    -0.09
     transfers
    -0.08
     Thornton
    -0.08
     accent
    -0.08
    gather
    -0.08
    ima
    -0.08
    urchase
    -0.08
     reun
    -0.08
    uet
    -0.07
    insurance
    -0.07
    POSITIVE LOGITS
    omy
    0.09
    ecs
    0.09
    aged
    0.09
    rewrite
    0.09
    ky
    0.09
    brief
    0.08
    ARSE
    0.08
     Typed
    0.08
    ÑĤом
    0.08
    king
    0.08
    Activations Density 0.001%

    No Known Activations