© 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. 48164
    Prev
    Next
    INDEX
    Explanations

    to be + past participle

    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
    insk
    -0.08
    inc
    -0.08
    è¢
    -0.08
     Harr
    -0.08
     being
    -0.08
     vow
    -0.08
     GL
    -0.08
     owe
    -0.07
     Being
    -0.07
    neau
    -0.07
    POSITIVE LOGITS
     feared
    0.14
     precise
    0.13
     ashamed
    0.12
     exact
    0.12
    ijing
    0.12
     reck
    0.11
     dreaded
    0.11
     pit
    0.11
     honest
    0.10
     sûr
    0.10
    Activations Density 0.085%

    No Known Activations