© 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. 31658
    Prev
    Next
    INDEX
    Explanations

    not followed by negation completion

    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
     nor
    -0.10
     rationale
    -0.10
     neither
    -0.10
     realities
    -0.10
     reality
    -0.10
     negativity
    -0.10
     negative
    -0.10
     Negative
    -0.10
     realistic
    -0.10
     negatively
    -0.10
    POSITIVE LOGITS
     uncommon
    0.13
     pleasant
    0.13
     exagger
    0.12
     surprising
    0.12
     fond
    0.11
     Friendly
    0.10
     surprise
    0.10
     bueno
    0.10
     miss
    0.10
     surprised
    0.10
    Activations Density 0.116%

    No Known Activations