© 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. 7595
    Prev
    Next
    INDEX
    Explanations

    positive evaluations of insights

    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
     stupid
    -0.17
     supposedly
    -0.14
     gossip
    -0.14
     weird
    -0.13
     useless
    -0.12
     crude
    -0.12
     boring
    -0.12
     stupidity
    -0.12
     sloppy
    -0.12
     mediocre
    -0.12
    POSITIVE LOGITS
     elo
    0.21
     thoughtful
    0.20
     articulate
    0.18
     insightful
    0.18
     insights
    0.15
     insight
    0.15
     nicely
    0.14
     beautifully
    0.14
     admirable
    0.14
     wonderfully
    0.13
    Activations Density 0.252%

    No Known Activations