© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 117226
    Prev
    Next
    INDEX
    Explanations

    your inbox or smartphone

    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
     Imperial
    -0.09
    ember
    -0.09
    amer
    -0.09
    ieg
    -0.09
     dj
    -0.09
    aste
    -0.08
    igm
    -0.08
     unc
    -0.08
    oad
    -0.08
     wastes
    -0.08
    POSITIVE LOGITS
     inbox
    0.10
     inertia
    0.10
     Inbox
    0.10
     fav
    0.10
     forehead
    0.10
    inbox
    0.10
     stocking
    0.09
     mailbox
    0.09
     Struct
    0.09
     Caucus
    0.09
    Activations Density 0.040%

    No Known Activations