© 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. 116461
    Prev
    Next
    INDEX
    Explanations

    challenges or unique experiences

    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
    opsy
    -0.09
     loving
    -0.08
    opa
    -0.08
     conc
    -0.08
     neglig
    -0.07
     cha
    -0.07
     Burk
    -0.07
    ebb
    -0.07
     suddenly
    -0.07
     lately
    -0.07
    POSITIVE LOGITS
     unparalleled
    0.25
     unprecedented
    0.23
     worthy
    0.20
     unmatched
    0.20
     worth
    0.19
     beyond
    0.19
     unlike
    0.17
     apl
    0.17
     greater
    0.17
     comparable
    0.16
    Activations Density 0.288%

    No Known Activations