© 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. 27158
    Prev
    Next
    INDEX
    Explanations

    patient comfort and agreement

    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
     seizing
    -0.09
     invitations
    -0.09
     Mö
    -0.09
     invites
    -0.09
     Victor
    -0.09
     thoughtful
    -0.09
     backstage
    -0.09
     Mou
    -0.09
     invite
    -0.09
     seize
    -0.08
    POSITIVE LOGITS
     uncomfortable
    0.15
     discomfort
    0.14
     uncomfort
    0.14
     comfort
    0.14
    comfort
    0.13
     Comfort
    0.13
     preference
    0.12
     confidentiality
    0.12
     Areas
    0.12
     preferences
    0.12
    Activations Density 0.023%

    No Known Activations