© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 2358
    Prev
    Next
    INDEX
    Explanations

    piston engines, tender engines, caliper bearings

    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
    ç½
    -0.10
    anc
    -0.09
    ICI
    -0.08
    kers
    -0.08
    atu
    -0.08
    su
    -0.08
    .sy
    -0.08
     Faul
    -0.08
     satur
    -0.08
     screening
    -0.07
    POSITIVE LOGITS
    -based
    0.11
    -driven
    0.09
     Aw
    0.09
     Dawn
    0.09
     dik
    0.08
    -Based
    0.08
     games
    0.08
    ixo
    0.08
     intimid
    0.08
    ä»ĺ
    0.08
    Activations Density 0.791%

    No Known Activations