© 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. 91012
    Prev
    Next
    INDEX
    Explanations

    ensure gender, privacy, and compliance

    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
     Zur
    -0.12
     Keller
    -0.12
    Ensure
    -0.11
    ota
    -0.11
    ril
    -0.11
    ests
    -0.11
     Pret
    -0.11
    /email
    -0.11
    ATURE
    -0.11
    estring
    -0.11
    POSITIVE LOGITS
     that
    0.10
    /prom
    0.09
     compliance
    0.08
    ered
    0.08
     maximum
    0.08
     greater
    0.08
     conformity
    0.08
     maximal
    0.07
     anonymity
    0.07
    ably
    0.07
    Activations Density 0.019%

    No Known Activations