© 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. 16416
    Prev
    Next
    INDEX
    Explanations

    new arrivals or additions

    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
     longstanding
    -0.12
     Existing
    -0.12
    Existing
    -0.12
     Gow
    -0.12
     existing
    -0.11
     faithful
    -0.11
     renew
    -0.11
    existing
    -0.10
     renewed
    -0.10
     vener
    -0.10
    POSITIVE LOGITS
     joining
    0.17
     arrivals
    0.15
     arrival
    0.14
     joins
    0.13
     join
    0.13
     arriving
    0.13
     arrived
    0.12
     replacing
    0.12
     replacements
    0.12
     addition
    0.12
    Activations Density 0.274%

    No Known Activations