© 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. 6125
    Prev
    Next
    INDEX
    Explanations

    Thursday after August

    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
     relay
    -0.12
     CNBC
    -0.10
     cnn
    -0.10
     ration
    -0.09
     BBC
    -0.09
    Reuters
    -0.09
     affiliates
    -0.09
     beta
    -0.09
    ledon
    -0.09
     Bilder
    -0.09
    POSITIVE LOGITS
     locally
    0.15
    KEEP
    0.15
    .EXP
    0.14
     Downtown
    0.13
     nightlife
    0.13
     Metro
    0.12
     ordinance
    0.12
     arts
    0.11
     scen
    0.11
    Metro
    0.11
    Activations Density 0.386%

    No Known Activations