© 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. 18156
    Prev
    Next
    INDEX
    Explanations

    depicted sex, filmed scenes

    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
     reminis
    -0.11
     memories
    -0.10
     Mari
    -0.10
     Memories
    -0.10
     outing
    -0.10
     tink
    -0.09
     memorial
    -0.09
     previous
    -0.09
     procrast
    -0.09
    kos
    -0.09
    POSITIVE LOGITS
     unrealistic
    0.25
     exaggerated
    0.24
     exagger
    0.20
     filmed
    0.20
     portrayed
    0.18
     unreal
    0.18
     depicted
    0.18
     filming
    0.18
     unnatural
    0.17
     portraying
    0.17
    Activations Density 0.066%

    No Known Activations