© 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. 14917
    Prev
    Next
    INDEX
    Explanations

    domestic violence, rape, gun violence, toxic stress, homelessness

    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
     homosexuals
    -0.14
     minorities
    -0.11
     homosexual
    -0.11
     fret
    -0.11
     policemen
    -0.10
     frowned
    -0.10
     homosexuality
    -0.09
    tern
    -0.09
     liberals
    -0.09
     melanch
    -0.09
    POSITIVE LOGITS
     harms
    0.17
     frontline
    0.14
     perpetrator
    0.13
     survivor
    0.13
     accessing
    0.13
     impacts
    0.12
     Dane
    0.12
     batter
    0.12
     tox
    0.12
     webinar
    0.11
    Activations Density 2.400%

    No Known Activations