© 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. 18599
    Prev
    Next
    INDEX
    Explanations

    guarantees or automatic results

    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
    uron
    -0.11
    iri
    -0.10
    asca
    -0.10
     Greenwood
    -0.10
     Vera
    -0.10
     Jennings
    -0.10
     Vere
    -0.10
     Spar
    -0.09
    entar
    -0.09
     everyday
    -0.09
    POSITIVE LOGITS
     magically
    0.18
     automatically
    0.16
     guarantee
    0.15
     suddenly
    0.15
     guaranteed
    0.14
     guarantees
    0.14
     automatic
    0.14
     Guarantee
    0.13
     mirac
    0.13
     guar
    0.13
    Activations Density 0.028%

    No Known Activations