© 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. 57302
    Prev
    Next
    INDEX
    Explanations

    programming errors

    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
     tent
    -0.07
    essor
    -0.07
     Yours
    -0.07
     mol
    -0.07
     alleges
    -0.07
     segreg
    -0.07
     implic
    -0.07
     Ak
    -0.07
     Strom
    -0.07
    iator
    -0.07
    POSITIVE LOGITS
    estruction
    0.10
    yll
    0.10
    adan
    0.09
    ock
    0.09
    gain
    0.09
    ining
    0.09
     subrange
    0.09
    ynet
    0.09
     Holdings
    0.09
     flesh
    0.09
    Activations Density 0.009%

    No Known Activations