© 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. 29462
    Prev
    Next
    INDEX
    Explanations

    timestamps and dashes

    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
    oled
    -0.11
    vic
    -0.11
    inqu
    -0.11
    .ld
    -0.11
     Transit
    -0.11
     azimuth
    -0.11
     flaming
    -0.10
     LOD
    -0.10
     vic
    -0.10
     Bark
    -0.10
    POSITIVE LOGITS
     end
    0.08
    vero
    0.08
    inan
    0.07
    retch
    0.07
     onward
    0.07
     advert
    0.07
     eternity
    0.07
     Nel
    0.07
     riv
    0.07
    jes
    0.07
    Activations Density 0.083%

    No Known Activations