© 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. 113948
    Prev
    Next
    INDEX
    Explanations

    Covington, Covaxis, covariant, covetise

    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
    CNN
    -0.09
    Wiki
    -0.09
     suit
    -0.09
    Liked
    -0.09
    ork
    -0.09
     LIS
    -0.08
    Kick
    -0.08
     lik
    -0.08
     dut
    -0.08
    CN
    -0.08
    POSITIVE LOGITS
     unbe
    0.09
     Unexpected
    0.09
     Bowman
    0.09
    aves
    0.09
    avers
    0.09
     Gott
    0.09
     Ring
    0.08
    ¶
    0.08
    YC
    0.08
    cher
    0.08
    Activations Density 0.002%

    No Known Activations