© 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. 113937
    Prev
    Next
    INDEX
    Explanations

    measurement in inches

    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
    eus
    -0.08
    .ba
    -0.08
    itas
    -0.08
    arie
    -0.08
    bro
    -0.08
    perf
    -0.08
    /per
    -0.08
    Dod
    -0.08
    ilen
    -0.08
    oure
    -0.08
    POSITIVE LOGITS
     diameter
    0.13
     knives
    0.10
    ledon
    0.10
     Pawn
    0.10
     ticking
    0.10
    hton
    0.10
     knife
    0.10
     longest
    0.10
     halo
    0.10
     sided
    0.10
    Activations Density 0.021%

    No Known Activations