© 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. 27556
    Prev
    Next
    INDEX
    Explanations

    newspaper names

    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
     Target
    -0.09
     targeted
    -0.09
     targeting
    -0.09
     disproportionately
    -0.08
    autop
    -0.08
    [source
    -0.08
    .Disclaimer
    -0.08
    yo
    -0.08
     CN
    -0.08
    Target
    -0.08
    POSITIVE LOGITS
     synonymous
    0.11
     companions
    0.10
     quotations
    0.09
     zw
    0.09
     companion
    0.09
    Threads
    0.09
     darling
    0.09
     guest
    0.09
     pers
    0.09
     Companion
    0.09
    Activations Density 0.001%

    No Known Activations