© 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. 25318
    Prev
    Next
    INDEX
    Explanations

    names like Gurinder, Gurley, Kurien, Korba

    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
    Not in Any Lists

    No Comments

    Negative Logits
    tin
    -0.11
    iams
    -0.11
    ncy
    -0.11
     angel
    -0.11
    lx
    -0.11
    rup
    -0.11
    eon
    -0.11
    labs
    -0.10
    ive
    -0.10
    iard
    -0.10
    POSITIVE LOGITS
     Aleks
    0.10
    unte
    0.09
     distr
    0.08
     lay
    0.08
    blo
    0.08
     Kor
    0.07
    opic
    0.07
    abo
    0.07
     neighb
    0.07
     intelligent
    0.07
    Activations Density 0.005%

    No Known Activations