© 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. 18242
    Prev
    Next
    INDEX
    Explanations

    toxic words and suffixes

    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
    /table
    -0.08
    ?v
    -0.08
    rows
    -0.08
    tle
    -0.08
     stocking
    -0.08
     libertine
    -0.08
    cion
    -0.07
     vais
    -0.07
    eki
    -0.07
    iac
    -0.07
    POSITIVE LOGITS
     masculinity
    0.17
    ology
    0.16
    ological
    0.16
    ities
    0.16
    ologically
    0.15
    ologist
    0.15
    ologists
    0.15
    icity
    0.15
    ity
    0.15
    okin
    0.14
    Activations Density 0.063%

    No Known Activations