© 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. 87766
    Prev
    Next
    INDEX
    Explanations

    amazing + noun

    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
    scale
    -0.11
     Gallagher
    -0.11
    GY
    -0.11
    age
    -0.11
    orian
    -0.10
    sie
    -0.10
    atan
    -0.10
    edException
    -0.10
    ernal
    -0.10
     ess
    -0.10
    POSITIVE LOGITS
    ness
    0.12
     feats
    0.11
     Grace
    0.10
    ment
    0.10
     grace
    0.10
    ely
    0.10
    ingly
    0.10
    -looking
    0.09
    ly
    0.09
    EMENT
    0.09
    Activations Density 0.010%

    No Known Activations