© 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. 90569
    Prev
    Next
    INDEX
    Explanations

    's steel production

    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
     ’
    -0.08
    ’T
    -0.08
    atrix
    -0.08
    ulti
    -0.08
     inv
    -0.08
    øj
    -0.08
    geh
    -0.08
     Sergei
    -0.08
    keit
    -0.07
    ever
    -0.07
    POSITIVE LOGITS
    sthrough
    0.11
     rall
    0.11
    sex
    0.11
    ssize
    0.11
    swith
    0.11
    sWith
    0.10
    sto
    0.10
     Hermes
    0.09
    ilen
    0.09
    ssc
    0.09
    Activations Density 0.020%

    No Known Activations