© 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. 29827
    Prev
    Next
    INDEX
    Explanations

    said [days of week/time]

    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
     stead
    -0.08
    /design
    -0.07
     lou
    -0.07
    ei
    -0.07
    override
    -0.07
     somew
    -0.06
     waist
    -0.06
    â
    -0.06
    assen
    -0.06
    ORED
    -0.06
    POSITIVE LOGITS
     goodbye
    0.12
    obl
    0.11
    quisitions
    0.11
    swire
    0.11
    enders
    0.11
     Wednesday
    0.11
     Tuesday
    0.10
     yesterday
    0.10
    dddd
    0.10
    mont
    0.10
    Activations Density 0.148%

    No Known Activations