© 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. 3584
    Prev
    Next
    INDEX
    Explanations

    how can this be

    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
    ori
    -0.11
    uve
    -0.11
     Miracle
    -0.11
    hor
    -0.11
     unlikely
    -0.11
    assi
    -0.11
    INC
    -0.10
    ongan
    -0.10
    BOUND
    -0.10
    erva
    -0.10
    POSITIVE LOGITS
     coincidence
    0.13
     possible
    0.11
     real
    0.10
     true
    0.10
     legit
    0.09
     Fritz
    0.09
     happening
    0.09
     kosher
    0.09
    possible
    0.09
     allowed
    0.09
    Activations Density 0.022%

    No Known Activations