© 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. 14068
    Prev
    Next
    INDEX
    Explanations

    world of

    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
     Started
    -0.10
    lette
    -0.10
    nop
    -0.10
     Marketable
    -0.10
    GIS
    -0.10
    liest
    -0.10
    ATHER
    -0.10
     Ruf
    -0.10
     alm
    -0.10
    mlink
    -0.09
    POSITIVE LOGITS
     Pall
    0.09
    <|endoftext|>
    0.08
     Kes
    0.08
     Domin
    0.07
     Tay
    0.07
    —you
    0.07
    arpa
    0.07
     Haw
    0.07
     bottom
    0.07
    asia
    0.07
    Activations Density 0.003%

    No Known Activations