© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5351
    Prev
    Next
    INDEX
    Explanations

    completion or error messages

    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
    asso
    -0.09
     dame
    -0.08
     Mour
    -0.08
    qid
    -0.08
    loom
    -0.07
    WI
    -0.07
    AI
    -0.07
    å¸
    -0.07
     flags
    -0.07
     paired
    -0.07
    POSITIVE LOGITS
    eka
    0.11
    Ars
    0.10
    ilog
    0.10
    Fatal
    0.10
    cen
    0.10
     Fatal
    0.10
     rhet
    0.10
    mailto
    0.10
     Stoke
    0.10
     Isle
    0.10
    Activations Density 0.001%

    No Known Activations