© 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. 28558
    Prev
    Next
    INDEX
    Explanations

    planning meetings and dates

    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
     CLUB
    -0.11
     weddings
    -0.11
    wed
    -0.11
     marrying
    -0.11
     wedding
    -0.10
     Mari
    -0.10
    Wed
    -0.10
     Bride
    -0.10
     Husband
    -0.10
     Marriage
    -0.10
    POSITIVE LOGITS
     initial
    0.12
     second
    0.11
     Initial
    0.10
    second
    0.10
     Casting
    0.10
     trial
    0.10
    ula
    0.09
     overnight
    0.09
    Initial
    0.09
     date
    0.09
    Activations Density 0.032%

    No Known Activations