© 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. 90505
    Prev
    Next
    INDEX
    Explanations

    alphanumeric sequences and symbols

    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
     Zah
    -0.10
     Innoc
    -0.10
     Laurent
    -0.09
     previews
    -0.08
     prod
    -0.08
    asaki
    -0.08
     Buffalo
    -0.08
     Gard
    -0.08
     edible
    -0.08
     casting
    -0.08
    POSITIVE LOGITS
     ers
    0.10
    Ending
    0.10
     sui
    0.10
    lops
    0.09
     comple
    0.09
    Äĥr
    0.09
    ington
    0.09
     variants
    0.08
     summed
    0.08
     mer
    0.08
    Activations Density 0.001%

    No Known Activations