© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 88187
    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
     Everett
    -0.08
    able
    -0.07
    idor
    -0.07
     Carter
    -0.07
    itta
    -0.07
    sing
    -0.06
     parach
    -0.06
     Extras
    -0.06
    -ever
    -0.06
    ables
    -0.06
    POSITIVE LOGITS
    ness
    0.17
    iap
    0.13
     Sent
    0.12
    upy
    0.12
    rum
    0.11
    457
    0.11
    -calendar
    0.11
     writ
    0.11
    emarks
    0.11
     enrol
    0.11
    Activations Density 0.003%

    No Known Activations