© 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. 31525
    Prev
    Next
    INDEX
    Explanations

    author of

    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
     pop
    -0.08
    ubi
    -0.08
    .wrap
    -0.08
     urgent
    -0.08
     Emin
    -0.08
     pound
    -0.08
     Mahm
    -0.08
    rog
    -0.07
     upset
    -0.07
     Dudley
    -0.07
    POSITIVE LOGITS
     fault
    0.10
    bung
    0.09
     dun
    0.09
    itution
    0.09
    alles
    0.09
    edi
    0.08
    Latch
    0.08
     args
    0.08
    енÑĮ
    0.08
     kak
    0.08
    Activations Density 0.032%

    No Known Activations