© 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. 46028
    Prev
    Next
    INDEX
    Explanations

    that, reason, else, enough, way, only

    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
     bon
    -0.10
    bon
    -0.09
    essler
    -0.09
     alf
    -0.08
     cand
    -0.08
    Fight
    -0.08
     parade
    -0.08
    arp
    -0.08
    åºı
    -0.08
    kke
    -0.08
    POSITIVE LOGITS
     Charl
    0.11
    ablo
    0.10
    ucher
    0.09
    lew
    0.09
     Cont
    0.09
    APS
    0.09
    UNS
    0.09
     defy
    0.09
    strand
    0.09
    -he
    0.09
    Activations Density 0.002%

    No Known Activations