© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90428
    Prev
    Next
    INDEX
    Explanations

    come to

    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
    ellig
    -0.07
    /he
    -0.07
     retention
    -0.07
     nu
    -0.07
     dia
    -0.07
     Advent
    -0.07
     Zimmerman
    -0.07
     arrival
    -0.07
     perse
    -0.07
     Rosenberg
    -0.07
    POSITIVE LOGITS
     grips
    0.17
     town
    0.15
     fruition
    0.14
     prominence
    0.13
     visit
    0.12
     realization
    0.12
     blows
    0.11
     casa
    0.11
     grief
    0.11
     interrog
    0.11
    Activations Density 0.046%

    No Known Activations