© 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. 89808
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

    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
     gaz
    -0.10
     regards
    -0.09
    /c
    -0.08
     thru
    -0.08
     aide
    -0.08
     nicely
    -0.08
    anne
    -0.08
     Cascade
    -0.08
     dept
    -0.08
     CFR
    -0.08
    POSITIVE LOGITS
     forcibly
    0.12
     meanwhile
    0.12
     retrospect
    0.12
     abroad
    0.12
     blink
    0.11
     secretly
    0.11
     systematically
    0.11
     alike
    0.11
    asan
    0.11
    ÑĤÑĮ
    0.10
    Activations Density 1.720%

    No Known Activations