© 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. 50966
    Prev
    Next
    INDEX
    Explanations

    my possessions

    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
    Negative Logits
     ours
    -0.19
     ourselves
    -0.15
     reportedly
    -0.15
     theirs
    -0.15
     presumably
    -0.13
     courtesy
    -0.13
     authors
    -0.12
    .We
    -0.12
     apparently
    -0.12
    —we
    -0.12
    POSITIVE LOGITS
     my
    0.28
    æĪijçļĦ
    0.24
    my
    0.20
     myself
    0.19
    æĪij
    0.18
    =my
    0.17
    	my
    0.17
    (my
    0.16
    -my
    0.16
     meine
    0.15
    Activations Density 1.415%

    No Known Activations