© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48033
    Prev
    Next
    INDEX
    Explanations

    relative or comparative relationships

    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
     preferably
    -0.10
     Samar
    -0.09
     worsh
    -0.09
    printStats
    -0.09
    ()][
    -0.09
     swe
    -0.09
     mentre
    -0.09
     incap
    -0.09
     tick
    -0.09
    entin
    -0.09
    POSITIVE LOGITS
     relative
    0.52
     compared
    0.51
     Relative
    0.42
    relative
    0.42
     Compared
    0.40
    Relative
    0.37
     comparatively
    0.34
    -relative
    0.31
    (relative
    0.29
     relatively
    0.28
    Activations Density 0.332%

    No Known Activations