© 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. 4750
    Prev
    Next
    INDEX
    Explanations

    dice rolls and random choices

    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
     randomly
    -0.10
     randomized
    -0.10
     randomness
    -0.09
    RANDOM
    -0.09
     random
    -0.09
     belts
    -0.09
     rnd
    -0.09
    random
    -0.08
    Random
    -0.08
     fle
    -0.08
    POSITIVE LOGITS
     persons
    0.12
     Polar
    0.11
    GST
    0.11
    ipp
    0.10
    .fr
    0.10
     pointing
    0.10
     Relatives
    0.10
     conserv
    0.10
     directing
    0.10
     gaz
    0.10
    Activations Density 0.005%

    No Known Activations