© 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. 6672
    Prev
    Next
    INDEX
    Explanations

    moral dilemmas, crime, moral issues

    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
     exacerb
    -0.10
     aggrav
    -0.10
    TRS
    -0.10
     unheard
    -0.10
    ildo
    -0.09
     flirting
    -0.09
     trim
    -0.09
     wid
    -0.09
     fatally
    -0.09
    556
    -0.09
    POSITIVE LOGITS
    rap
    0.09
     vag
    0.09
     Greenwood
    0.09
     milieu
    0.09
    IFT
    0.09
    ift
    0.09
    intestinal
    0.08
     pitfalls
    0.08
     Sle
    0.08
     bust
    0.08
    Activations Density 0.001%

    No Known Activations