© 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. 25795
    Prev
    Next
    INDEX
    Explanations

    percentages and small numbers

    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
     majority
    -0.15
     halfway
    -0.11
    HU
    -0.10
    auer
    -0.10
     informal
    -0.10
     MLA
    -0.09
     Semi
    -0.09
     predominant
    -0.09
     Linden
    -0.09
    isel
    -0.09
    POSITIVE LOGITS
     (<
    0.18
     miscellaneous
    0.17
     rare
    0.17
     outliers
    0.16
     negligible
    0.16
     Rare
    0.15
     outlier
    0.14
     Miscellaneous
    0.13
    Rare
    0.13
     remainder
    0.13
    Activations Density 0.739%

    No Known Activations