© 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. 30195
    Prev
    Next
    INDEX
    Explanations

    heterosexual, omnivory, exclusively

    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
     forbidden
    -0.11
     unmarried
    -0.11
     leisure
    -0.11
     illicit
    -0.10
     interracial
    -0.10
     divorced
    -0.10
     sterile
    -0.10
     arcade
    -0.10
     multiline
    -0.09
     illeg
    -0.09
    POSITIVE LOGITS
     conventional
    0.21
     traditional
    0.16
     heterosexual
    0.15
     normal
    0.15
     conform
    0.14
     Traditional
    0.14
     convention
    0.13
    Traditional
    0.13
    normal
    0.13
     mainstream
    0.12
    Activations Density 0.112%

    No Known Activations