© 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. 111535
    Prev
    Next
    INDEX
    Explanations

    to followed by a verb

    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
    /ca
    -0.10
    aste
    -0.09
     bothered
    -0.09
    oun
    -0.08
     *}
    -0.08
    RPC
    -0.08
     accompl
    -0.08
    anch
    -0.08
     Roo
    -0.08
    aby
    -0.07
    POSITIVE LOGITS
     simply
    0.18
     somehow
    0.14
     simplement
    0.12
     Simply
    0.12
     constantly
    0.11
    Simply
    0.11
     carefully
    0.11
     always
    0.10
    variation
    0.10
     actually
    0.10
    Activations Density 0.100%

    No Known Activations