© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 87934
    Prev
    Next
    INDEX
    Explanations

    the abstract noun

    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
     exciting
    -0.12
     intriguing
    -0.11
     controversial
    -0.11
    interesting
    -0.10
     benefit
    -0.10
     problematic
    -0.10
     handsome
    -0.10
     fascinating
    -0.10
     promising
    -0.09
     interesting
    -0.09
    POSITIVE LOGITS
     thought
    0.20
     consequences
    0.18
     hassle
    0.18
     Thought
    0.16
     implications
    0.15
    thought
    0.14
     costs
    0.14
     cost
    0.14
     noise
    0.13
     repercussions
    0.13
    Activations Density 0.067%

    No Known Activations