© 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. 24950
    Prev
    Next
    INDEX
    Explanations

    Sylv/ylv followed by ia/ester/atica

    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
     courtesy
    -0.09
     copies
    -0.08
     vandal
    -0.08
     misunderstanding
    -0.08
     tanks
    -0.08
     respectively
    -0.08
     Rotary
    -0.08
     tasting
    -0.07
    267
    -0.07
     ries
    -0.07
    POSITIVE LOGITS
    arent
    0.11
    <dd
    0.10
     incons
    0.10
     gradu
    0.10
    CJK
    0.10
     umbrella
    0.10
     pinned
    0.10
    umbn
    0.10
    alah
    0.10
    -break
    0.10
    Activations Density 0.001%

    No Known Activations