© 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. 25584
    Prev
    Next
    INDEX
    Explanations

    opportunity

    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
    Vari
    -0.10
    utsch
    -0.10
     AtomicInteger
    -0.10
     Ronald
    -0.09
    horn
    -0.09
     Neil
    -0.09
     todd
    -0.09
    077
    -0.09
    lok
    -0.09
     hex
    -0.09
    POSITIVE LOGITS
     opportunity
    0.27
     opportunities
    0.24
     Opportunity
    0.22
     Opportunities
    0.22
     opport
    0.15
     OPP
    0.15
     ripe
    0.13
     opportun
    0.13
     oportun
    0.13
     Opport
    0.11
    Activations Density 0.040%

    No Known Activations