© 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. 48619
    Prev
    Next
    INDEX
    Explanations

    questions about ownership or authentication

    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
     elsewhere
    -0.10
    xEC
    -0.09
     expected
    -0.09
     desired
    -0.08
     Stout
    -0.08
    arem
    -0.08
     dis
    -0.08
     ez
    -0.08
    communic
    -0.08
     IMD
    -0.08
    POSITIVE LOGITS
    anes
    0.11
    |R
    0.10
     numbering
    0.10
     Malone
    0.10
    /use
    0.09
    olio
    0.09
    |%
    0.09
    ookies
    0.09
     Craig
    0.09
    ring
    0.09
    Activations Density 0.006%

    No Known Activations