© 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. 3183
    Prev
    Next
    INDEX
    Explanations

    Meyyar Thirumeyyam

    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
    ajs
    -0.10
    olas
    -0.10
    erville
    -0.09
    hunter
    -0.09
     Baths
    -0.09
    ÑģÑĤÑĢÑĥк
    -0.09
    ém
    -0.09
    estate
    -0.09
    acz
    -0.09
    omas
    -0.09
    POSITIVE LOGITS
    nore
    0.10
     hung
    0.07
    hip
    0.07
    sass
    0.07
     Lynch
    0.07
    inv
    0.07
    conc
    0.07
    map
    0.06
     Fletcher
    0.06
    rab
    0.06
    Activations Density 0.436%

    No Known Activations