© 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. 30815
    Prev
    Next
    INDEX
    Explanations

    negative experiences or control

    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
    Mounted
    -0.10
     midd
    -0.09
     ancest
    -0.09
     grues
    -0.09
     middle
    -0.09
    kker
    -0.09
     ende
    -0.08
     halfway
    -0.08
     Reach
    -0.08
     horny
    -0.08
    POSITIVE LOGITS
     humiliation
    0.15
     isolation
    0.13
     forced
    0.13
    forced
    0.12
     imprisonment
    0.12
     manipulation
    0.11
     slavery
    0.11
     nudity
    0.11
     confinement
    0.10
     controlled
    0.10
    Activations Density 0.012%

    No Known Activations