© 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. 46881
    Prev
    Next
    INDEX
    Explanations

    plastic surgery

    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
     lub
    -0.13
     subscribe
    -0.13
     subscribed
    -0.12
     Kund
    -0.11
     subscribing
    -0.11
    -gay
    -0.11
     Cutter
    -0.11
     Herc
    -0.10
     Subscribe
    -0.10
     subscri
    -0.10
    POSITIVE LOGITS
     aesthetic
    0.21
     surgeon
    0.19
     surgeons
    0.17
     aesthetics
    0.17
     aest
    0.16
     candidacy
    0.15
     cosmetic
    0.14
     implant
    0.14
     Cosmetic
    0.14
     reconstruct
    0.14
    Activations Density 2.208%

    No Known Activations