© 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. 13880
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

    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
     Finder
    -0.08
     Eyes
    -0.08
    feld
    -0.08
    stakes
    -0.08
     fv
    -0.08
     Nunes
    -0.08
    ,args
    -0.08
    vd
    -0.08
     Trom
    -0.08
    698
    -0.08
    POSITIVE LOGITS
    olid
    0.10
     perfectly
    0.10
     meas
    0.10
    "":
    0.10
    iare
    0.09
     waist
    0.09
    chan
    0.09
    erce
    0.09
     inher
    0.09
     circumference
    0.09
    Activations Density 0.027%

    No Known Activations