© 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. 47444
    Prev
    Next
    INDEX
    Explanations

    probability and randomness

    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
     Abel
    -0.12
     Liber
    -0.10
    504
    -0.10
    510
    -0.10
     HALF
    -0.09
    /dir
    -0.09
     Toe
    -0.09
    dg
    -0.09
    enge
    -0.09
    ibble
    -0.09
    POSITIVE LOGITS
     unlucky
    0.35
     luck
    0.31
     randomly
    0.31
     randomized
    0.26
     random
    0.26
     Luck
    0.24
     lucky
    0.23
     randomness
    0.23
     Random
    0.23
    random
    0.21
    Activations Density 0.387%

    No Known Activations