© 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. 50938
    Prev
    Next
    INDEX
    Explanations

    next to

    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
    erc
    -0.10
    urr
    -0.09
    umu
    -0.09
     Mum
    -0.09
    765
    -0.09
    972
    -0.09
     halfway
    -0.09
    dek
    -0.09
    ador
    -0.09
    thon
    -0.09
    POSITIVE LOGITS
     Impossible
    0.12
     impossible
    0.11
    Impossible
    0.10
     Realty
    0.09
     worthless
    0.09
    gend
    0.09
    /on
    0.09
     useless
    0.08
     rubble
    0.08
    door
    0.08
    Activations Density 0.023%

    No Known Activations