© 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. 27945
    Prev
    Next
    INDEX
    Explanations

    not influenced by bias

    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
    pel
    -0.10
     Bedroom
    -0.10
    511
    -0.10
    csi
    -0.10
     bedrooms
    -0.10
     bedroom
    -0.10
    281
    -0.10
     misunderstood
    -0.10
    uled
    -0.10
     ade
    -0.09
    POSITIVE LOGITS
     biased
    0.72
     bias
    0.72
     Bias
    0.62
     biases
    0.60
    bias
    0.54
    biased
    0.52
    Bias
    0.51
     unbiased
    0.50
     impartial
    0.38
    _bias
    0.38
    Activations Density 0.277%

    No Known Activations