© 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. 6932
    Prev
    Next
    INDEX
    Explanations

    scandalous or scandalizing

    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
    elon
    -0.09
     agon
    -0.09
    Ùij
    -0.08
    enu
    -0.08
    urement
    -0.08
    tings
    -0.08
    nings
    -0.08
    'er
    -0.08
    kinson
    -0.07
    ention
    -0.07
    POSITIVE LOGITS
    ous
    0.27
    ously
    0.22
    ized
    0.19
    ize
    0.17
    OUS
    0.15
    ised
    0.13
    izing
    0.13
     scandal
    0.13
    ically
    0.12
    ouse
    0.12
    Activations Density 0.006%

    No Known Activations