© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 46201
    Prev
    Next
    INDEX
    Explanations

    unexpected 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
    Negative Logits
    itan
    -0.11
     femin
    -0.10
    ieten
    -0.10
     Talks
    -0.10
    engo
    -0.10
    rst
    -0.10
    /Open
    -0.10
     penetrated
    -0.10
     unint
    -0.10
     Colomb
    -0.10
    POSITIVE LOGITS
     sometimes
    0.18
    sometimes
    0.15
     Sometimes
    0.14
     unexpected
    0.14
     often
    0.13
    Sometimes
    0.13
     unintended
    0.12
     choices
    0.12
     Unexpected
    0.11
     dreams
    0.11
    Activations Density 0.202%

    No Known Activations