© 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. 87847
    Prev
    Next
    INDEX
    Explanations

    in [followed by description]

    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
     hindsight
    -0.11
    oma
    -0.10
    uba
    -0.09
     lay
    -0.09
     regards
    -0.09
     Bid
    -0.08
     terme
    -0.08
    idge
    -0.08
     lab
    -0.08
    orama
    -0.07
    POSITIVE LOGITS
     behalf
    0.16
     consequence
    0.13
    andr
    0.13
     connexion
    0.13
     latitude
    0.12
     divers
    0.11
    ants
    0.11
     conformity
    0.11
    iqu
    0.11
     despite
    0.11
    Activations Density 0.240%

    No Known Activations