© 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. 13847
    Prev
    Next
    INDEX
    Explanations

    win or

    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
    vable
    -0.09
     peripheral
    -0.09
     lateral
    -0.08
     impaired
    -0.08
    urf
    -0.08
    upal
    -0.08
     binary
    -0.08
     inhabited
    -0.08
    ãģĪ
    -0.08
     libraries
    -0.08
    POSITIVE LOGITS
     Klo
    0.10
     interim
    0.09
     Coco
    0.09
    oft
    0.09
     Parade
    0.09
    dre
    0.08
     loophole
    0.08
     ky
    0.08
     Mic
    0.08
    OTH
    0.08
    Activations Density 0.002%

    No Known Activations