© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48799
    Prev
    Next
    INDEX
    Explanations

    parents or spouse

    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
     girl
    -0.13
     woman
    -0.13
     girls
    -0.11
    女
    -0.10
     women
    -0.10
     lesbian
    -0.10
     Johannes
    -0.10
     Girl
    -0.09
     Girls
    -0.09
     Woman
    -0.09
    POSITIVE LOGITS
     wives
    0.14
     Sus
    0.14
     Zoo
    0.12
     Aura
    0.12
     Charity
    0.12
     wife
    0.12
     trophy
    0.12
     Polly
    0.11
     Annunci
    0.11
     Aurora
    0.11
    Activations Density 0.415%

    No Known Activations