© 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. 115090
    Prev
    Next
    INDEX
    Explanations

    updates and findings

    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
     dep
    -0.08
    556
    -0.07
    ipa
    -0.07
     Kov
    -0.07
     passing
    -0.07
    imo
    -0.07
     Bobby
    -0.07
    IMO
    -0.07
     introduced
    -0.06
     deprecated
    -0.06
    POSITIVE LOGITS
     progress
    0.26
     results
    0.24
     Results
    0.22
     Progress
    0.22
     updates
    0.21
    progress
    0.21
     news
    0.20
    results
    0.20
    Results
    0.20
     findings
    0.19
    Activations Density 0.309%

    No Known Activations