© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 30986
    Prev
    Next
    INDEX
    Explanations

    names starting with 'A' or 'D'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fty
    -0.10
     sire
    -0.10
     fir
    -0.10
    %^
    -0.10
     coup
    -0.10
     appealed
    -0.10
    ades
    -0.09
     fills
    -0.09
     blessed
    -0.09
     struck
    -0.09
    POSITIVE LOGITS
    emouth
    0.12
    orer
    0.10
    bart
    0.09
    /address
    0.08
    etta
    0.08
     beside
    0.08
     Violet
    0.08
     Bers
    0.08
     Cron
    0.08
    shire
    0.08
    Activations Density 0.645%

    No Known Activations