© 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. 87967
    Prev
    Next
    INDEX
    Explanations

    free software 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
    Not in Any Lists

    No Comments

    Negative Logits
    antes
    -0.08
     Doctors
    -0.08
     pull
    -0.07
    antz
    -0.07
    abad
    -0.07
     inverted
    -0.07
     Lesb
    -0.07
     uncont
    -0.07
     Strat
    -0.07
    )V
    -0.07
    POSITIVE LOGITS
    ari
    0.11
     youre
    0.11
     Rights
    0.10
     Zimmer
    0.10
     housed
    0.10
    Emb
    0.10
    apper
    0.10
    798
    0.10
     caring
    0.10
     pam
    0.10
    Activations Density 0.001%

    No Known Activations