© 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. 14648
    Prev
    Next
    INDEX
    Explanations

    ethical, legal, political, moral

    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
    enne
    -0.09
    isin
    -0.09
    cil
    -0.09
    velle
    -0.09
     cé
    -0.09
    aje
    -0.08
    jj
    -0.08
     sécur
    -0.08
     Pipe
    -0.08
     Territories
    -0.08
    POSITIVE LOGITS
     dile
    0.12
     eth
    0.10
     fatt
    0.10
     unb
    0.09
     pragma
    0.09
     unethical
    0.09
     Practices
    0.09
     Eth
    0.08
     aesthetics
    0.08
     unp
    0.08
    Activations Density 0.077%

    No Known Activations