© 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. 27157
    Prev
    Next
    INDEX
    Explanations

    obedience and defiance

    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
     unstoppable
    -0.11
     compliments
    -0.11
     compliment
    -0.11
     friendly
    -0.11
     empowered
    -0.11
     omnip
    -0.11
    friendly
    -0.11
     Gentle
    -0.10
     Friendly
    -0.10
     buddies
    -0.10
    POSITIVE LOGITS
     ripe
    0.17
     obedient
    0.14
     resisting
    0.14
     obedience
    0.14
     virgin
    0.14
     terrified
    0.13
     defiant
    0.13
     potential
    0.12
     naï
    0.12
     submissive
    0.12
    Activations Density 0.012%

    No Known Activations