© 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. 13935
    Prev
    Next
    INDEX
    Explanations

    the + noun

    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
     Sto
    -0.09
    azi
    -0.09
     Equals
    -0.09
     fruitful
    -0.09
    sanitize
    -0.09
    extent
    -0.09
     Ek
    -0.08
    ICA
    -0.08
     bases
    -0.08
    areth
    -0.08
    POSITIVE LOGITS
     situation
    0.20
     situations
    0.16
     Situation
    0.14
    æĥħ
    0.13
     moment
    0.11
    nym
    0.11
    oven
    0.11
     relationship
    0.11
     occasion
    0.11
    thing
    0.11
    Activations Density 0.150%

    No Known Activations