© 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. 92490
    Prev
    Next
    INDEX
    Explanations

    license 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
     warmed
    -0.10
    RIA
    -0.10
    IJ
    -0.10
    altet
    -0.10
    zilla
    -0.10
    Liked
    -0.10
     Ari
    -0.10
    _salt
    -0.10
    anding
    -0.09
     salt
    -0.09
    POSITIVE LOGITS
     Suk
    0.10
     Humb
    0.09
     Bez
    0.09
     mult
    0.08
     Sus
    0.08
     Bes
    0.08
     Peel
    0.08
     Bri
    0.08
     Boots
    0.08
     Surre
    0.08
    Activations Density 0.115%

    No Known Activations