© 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. 113831
    Prev
    Next
    INDEX
    Explanations

    file license

    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
    aws
    -0.10
    aks
    -0.09
    brook
    -0.09
    iner
    -0.09
    ags
    -0.09
     outr
    -0.09
     turf
    -0.09
    areth
    -0.09
    Downloads
    -0.09
     Hell
    -0.08
    POSITIVE LOGITS
     immoral
    0.09
     Accord
    0.09
    ··
    0.08
     Ziel
    0.08
     sacrific
    0.08
     McConnell
    0.08
     Forward
    0.08
    elp
    0.08
    (Spring
    0.08
     supp
    0.08
    Activations Density 0.002%

    No Known Activations