© 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. 92659
    Prev
    Next
    INDEX
    Explanations

    derogatory terms or relief

    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
     conver
    -0.11
    cri
    -0.10
    -disable
    -0.09
     Sin
    -0.09
    inh
    -0.09
    axe
    -0.09
    _extensions
    -0.09
     Combination
    -0.09
     retire
    -0.09
     Cro
    -0.09
    POSITIVE LOGITS
    weg
    0.09
    warf
    0.09
     overs
    0.09
    olds
    0.08
     oversh
    0.08
     incarcerated
    0.08
     Hou
    0.08
     nar
    0.08
    alam
    0.07
    ìĿ¸
    0.07
    Activations Density 0.001%

    No Known Activations