© 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. 3536
    Prev
    Next
    INDEX
    Explanations

    shapes or descriptions often followed by another word

    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
     guid
    -0.09
     Far
    -0.09
    lags
    -0.08
    utt
    -0.08
    far
    -0.08
    Far
    -0.08
    lashes
    -0.08
    qualities
    -0.08
    fir
    -0.08
     Above
    -0.08
    POSITIVE LOGITS
     she
    0.08
     outs
    0.08
    roe
    0.08
    Yo
    0.08
     Portuguese
    0.08
     aug
    0.08
    ased
    0.08
     Guerrero
    0.08
    rh
    0.08
     qua
    0.08
    Activations Density 0.625%

    No Known Activations