© 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. 3775
    Prev
    Next
    INDEX
    Explanations

    It's / It is / It was

    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
    elic
    -0.13
     tether
    -0.11
     Huck
    -0.11
    elle
    -0.10
    iphone
    -0.09
    ar
    -0.09
    ãĤ°
    -0.09
     sai
    -0.09
     consum
    -0.09
    (big
    -0.09
    POSITIVE LOGITS
     quieter
    0.15
     warmer
    0.12
     warmed
    0.12
     colder
    0.11
     Ves
    0.11
    reminder
    0.10
     paradise
    0.10
     quiet
    0.10
     humid
    0.10
     Busy
    0.10
    Activations Density 0.058%

    No Known Activations