© 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. 116020
    Prev
    Next
    INDEX
    Explanations

    likelihood of outcome

    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
    alten
    -0.11
    argo
    -0.10
    engo
    -0.10
    wis
    -0.10
    Alias
    -0.10
    aki
    -0.10
    uci
    -0.09
     wn
    -0.09
    eed
    -0.09
    ghan
    -0.09
    POSITIVE LOGITS
     chances
    0.51
     likelihood
    0.48
     potentially
    0.45
     potential
    0.41
     likely
    0.39
     possibility
    0.38
     probability
    0.37
     Likely
    0.36
     guaranteed
    0.35
     chance
    0.35
    Activations Density 1.188%

    No Known Activations