© 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. 15459
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by obligation

    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
     felt
    -0.12
     feeling
    -0.12
     prefer
    -0.11
     feels
    -0.11
    felt
    -0.11
     want
    -0.11
     wants
    -0.11
     Kear
    -0.11
     bele
    -0.10
     Wants
    -0.10
    POSITIVE LOGITS
     should
    0.17
    should
    0.15
     shouldn
    0.15
     Should
    0.15
     ought
    0.13
    Should
    0.12
     SHOULD
    0.12
     долж
    0.12
    ucks
    0.10
     miscon
    0.10
    Activations Density 0.155%

    No Known Activations