© 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. 46870
    Prev
    Next
    INDEX
    Explanations

    testing and verifying capabilities

    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
     giveaway
    -0.09
     litter
    -0.09
     Soon
    -0.09
     sanctioned
    -0.09
     hike
    -0.08
     Nob
    -0.08
     dignity
    -0.08
     arist
    -0.08
    kers
    -0.08
    /Gate
    -0.08
    POSITIVE LOGITS
     effectiveness
    0.21
     efficacy
    0.20
     capabilities
    0.19
     limits
    0.18
     abilities
    0.17
     Limits
    0.17
    limits
    0.16
     hypothesis
    0.16
     capability
    0.15
     effects
    0.15
    Activations Density 0.593%

    No Known Activations