© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 28293
    Prev
    Next
    INDEX
    Explanations

    then I will

    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
     now
    -0.14
     prere
    -0.13
     ahora
    -0.12
    EFR
    -0.12
     Cannot
    -0.12
    -dot
    -0.12
     oversh
    -0.11
    now
    -0.11
    )did
    -0.11
     Kra
    -0.11
    POSITIVE LOGITS
     will
    0.16
     hopefully
    0.14
     shall
    0.14
    will
    0.12
     Hopefully
    0.12
     we
    0.11
     THEN
    0.11
    hopefully
    0.11
    ä¼ļ
    0.11
     ill
    0.11
    Activations Density 0.038%

    No Known Activations