© 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. 3979
    Prev
    Next
    INDEX
    Explanations

    email unless

    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
     Never
    -0.12
     lifetime
    -0.11
     frü
    -0.11
     Blackburn
    -0.11
     denn
    -0.11
     DEN
    -0.10
     später
    -0.10
     Kro
    -0.10
     earlier
    -0.10
     unp
    -0.10
    POSITIVE LOGITS
     temporarily
    0.13
     anymore
    0.13
     until
    0.12
    until
    0.11
     awhile
    0.11
     sage
    0.09
     lately
    0.09
     nau
    0.09
    cede
    0.09
     anything
    0.08
    Activations Density 0.202%

    No Known Activations