© 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. 114522
    Prev
    Next
    INDEX
    Explanations

    introductions and personal greetings

    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
     firsthand
    -0.09
     vic
    -0.09
     sed
    -0.08
     syn
    -0.08
    vd
    -0.08
     consequ
    -0.08
     SYN
    -0.08
    essler
    -0.08
     advancement
    -0.08
    fect
    -0.08
    POSITIVE LOGITS
     pleased
    0.16
    leased
    0.13
     glad
    0.13
     spelled
    0.12
    ple
    0.12
    utton
    0.11
     Nice
    0.10
     pleasure
    0.10
     nice
    0.10
    ople
    0.10
    Activations Density 0.020%

    No Known Activations