© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48471
    Prev
    Next
    INDEX
    Explanations

    example, case, instance

    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
     Osborne
    -0.09
     SZ
    -0.09
    uala
    -0.09
    ordin
    -0.09
    IFn
    -0.08
    .assets
    -0.08
     pij
    -0.08
     analogue
    -0.08
     Alic
    -0.08
     sola
    -0.08
    POSITIVE LOGITS
     ones
    0.22
     ours
    0.16
     yours
    0.14
     exempl
    0.14
     aforementioned
    0.13
     example
    0.13
     recent
    0.13
    ones
    0.12
     case
    0.12
     fortunately
    0.12
    Activations Density 0.192%

    No Known Activations