© 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. 34058
    Prev
    Next
    INDEX
    Explanations

    improvisation, improving, imprudence, implausible

    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
    å±
    -0.11
    /co
    -0.11
     appar
    -0.11
    asel
    -0.10
    ively
    -0.10
     pall
    -0.10
    esis
    -0.10
    jer
    -0.10
     Ain
    -0.10
     Ark
    -0.10
    POSITIVE LOGITS
    s
    0.09
     spontaneously
    0.08
     straight
    0.08
    merce
    0.08
     recreated
    0.07
    illis
    0.07
     nightly
    0.07
     toys
    0.07
     repr
    0.07
     Straight
    0.07
    Activations Density 0.014%

    No Known Activations