© 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. 17805
    Prev
    Next
    INDEX
    Explanations

    feminism and gender equality

    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
     secretive
    -0.12
     secrecy
    -0.12
     nos
    -0.11
     gambling
    -0.11
     crypt
    -0.11
     illicit
    -0.10
     liquidity
    -0.10
     confession
    -0.10
     curiosity
    -0.10
     Gambling
    -0.10
    POSITIVE LOGITS
     feminist
    0.53
     feminism
    0.49
     feminists
    0.47
     Femin
    0.41
     sexist
    0.37
     sexism
    0.36
     misogyn
    0.35
     Gender
    0.33
     misog
    0.33
     gender
    0.31
    Activations Density 0.281%

    No Known Activations