© 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. 4467
    Prev
    Next
    INDEX
    Explanations

    market segmentation and consumption

    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
     pimp
    -0.11
     Extras
    -0.10
    -readable
    -0.09
    icare
    -0.09
    fir
    -0.09
     Guantanamo
    -0.09
     Gratuit
    -0.09
     mush
    -0.09
     sle
    -0.09
     capitalism
    -0.09
    POSITIVE LOGITS
     segmentation
    0.19
     segment
    0.17
     Segment
    0.17
     segments
    0.17
     segmented
    0.16
     penetration
    0.15
     penetrated
    0.15
     cann
    0.15
     consumers
    0.15
     consumption
    0.15
    Activations Density 1.680%

    No Known Activations