© 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. 87640
    Prev
    Next
    INDEX
    Explanations

    ja

    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
    iji
    -0.08
    a
    -0.08
    ller
    -0.08
     vere
    -0.08
    tre
    -0.08
     sender
    -0.08
     punishing
    -0.08
     Rough
    -0.08
    pter
    -0.07
     Joey
    -0.07
    POSITIVE LOGITS
     topical
    0.10
     tack
    0.10
     sectional
    0.10
    åIJ«
    0.10
    ogg
    0.10
    quez
    0.09
    qc
    0.09
    prises
    0.09
    enic
    0.09
    egers
    0.09
    Activations Density 0.027%

    No Known Activations