© 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. 50837
    Prev
    Next
    INDEX
    Explanations

    list item separator

    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
     intent
    -0.09
     barg
    -0.09
     amy
    -0.09
    .mas
    -0.09
     ($(
    -0.08
     cred
    -0.08
     intents
    -0.08
    arten
    -0.08
     mind
    -0.08
     apost
    -0.08
    POSITIVE LOGITS
     although
    0.17
     apart
    0.15
     besides
    0.15
     except
    0.13
     coupled
    0.13
     whenever
    0.12
     it
    0.12
     there
    0.11
     firstly
    0.11
    although
    0.11
    Activations Density 0.071%

    No Known Activations