© 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. 25136
    Prev
    Next
    INDEX
    Explanations

    in short, in sum, in brief, in a nutshell, in simple terms

    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
    -0.09
     unt
    -0.09
    aso
    -0.08
    acos
    -0.08
    avers
    -0.08
     Unt
    -0.08
     unb
    -0.07
     stale
    -0.07
    sx
    -0.07
     Rolling
    -0.07
    POSITIVE LOGITS
    anke
    0.11
     strokes
    0.11
    :
    0.10
     words
    0.10
    case
    0.10
    RAL
    0.10
    ANTA
    0.10
     everything
    0.09
     everywhere
    0.09
     encaps
    0.09
    Activations Density 0.011%

    No Known Activations