© 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. 91704
    Prev
    Next
    INDEX
    Explanations

    so, consequently, interestingly

    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
     ima
    -0.09
    izzy
    -0.09
     thighs
    -0.09
    strand
    -0.09
     Sunder
    -0.09
    bdd
    -0.09
     WHY
    -0.08
     Lem
    -0.08
     Saying
    -0.08
    adt
    -0.08
    POSITIVE LOGITS
     so
    0.23
     Interesting
    0.20
    Interesting
    0.20
     evidently
    0.20
     So
    0.19
     apparently
    0.19
    So
    0.18
     Apparently
    0.18
    Apparently
    0.17
     interesting
    0.17
    Activations Density 0.020%

    No Known Activations