© 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. 114478
    Prev
    Next
    INDEX
    Explanations

    precise summary evaluation

    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
    Stories
    -0.13
     Stories
    -0.10
    alia
    -0.10
    onta
    -0.10
    imin
    -0.09
     revisions
    -0.09
     Tested
    -0.09
     assured
    -0.09
    stories
    -0.09
    Oops
    -0.09
    POSITIVE LOGITS
     succinct
    0.31
     summed
    0.26
     accurately
    0.26
     elo
    0.25
     exactly
    0.25
     summarizes
    0.24
     sums
    0.24
     apt
    0.24
     nailed
    0.23
     Exactly
    0.22
    Activations Density 0.211%

    No Known Activations