© 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. 112527
    Prev
    Next
    INDEX
    Explanations

    socially induced stress

    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
     conventions
    -0.10
     feminist
    -0.09
     conventional
    -0.09
     traditional
    -0.08
     FM
    -0.08
     Higgins
    -0.08
     sausage
    -0.07
     arg
    -0.07
     intimid
    -0.07
     Duck
    -0.07
    POSITIVE LOGITS
     legitimate
    0.13
     virt
    0.13
     virgin
    0.13
     redeem
    0.12
     ideally
    0.12
     potency
    0.12
     embod
    0.12
     legitimacy
    0.12
     preferably
    0.11
     souls
    0.11
    Activations Density 0.132%

    No Known Activations