© 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. 113592
    Prev
    Next
    INDEX
    Explanations

    don't care

    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
    ubar
    -0.11
    @s
    -0.10
    esp
    -0.10
    icl
    -0.10
    lite
    -0.10
    cab
    -0.10
     acc
    -0.09
     Pra
    -0.09
     lite
    -0.09
     col
    -0.09
    POSITIVE LOGITS
     cares
    0.54
     cared
    0.50
     care
    0.48
     caring
    0.48
     indifferent
    0.41
     indifference
    0.40
     Care
    0.38
    -care
    0.34
    care
    0.33
    Care
    0.33
    Activations Density 0.149%

    No Known Activations