© 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. 4589
    Prev
    Next
    INDEX
    Explanations

    market research segments commodities

    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
    cached
    -0.11
     markets
    -0.10
     caching
    -0.09
    aura
    -0.09
     mega
    -0.09
     propaganda
    -0.09
    itchens
    -0.08
    zac
    -0.08
     multiplic
    -0.08
     marketed
    -0.08
    POSITIVE LOGITS
     segmentation
    0.11
     goods
    0.11
    segment
    0.10
     commodities
    0.10
    uttle
    0.10
     forces
    0.10
     Seg
    0.10
     saturation
    0.10
     segments
    0.09
     segmented
    0.09
    Activations Density 0.211%

    No Known Activations