© 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. 92541
    Prev
    Next
    INDEX
    Explanations

    date, time, place, methods

    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
     defensively
    -0.10
    oko
    -0.10
     Suffolk
    -0.10
     defenders
    -0.10
    oft
    -0.10
    ressing
    -0.10
     Cle
    -0.09
     Zwe
    -0.09
     wor
    -0.09
    ño
    -0.09
    POSITIVE LOGITS
    /method
    0.10
     intent
    0.08
    iton
    0.08
     MILF
    0.08
    /button
    0.08
    VEC
    0.08
     Spare
    0.08
     disguised
    0.08
     sore
    0.08
     privile
    0.08
    Activations Density 2.035%

    No Known Activations