© 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. 113446
    Prev
    Next
    INDEX
    Explanations

    categorizing and organizing information

    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
    arda
    -0.13
     EIF
    -0.10
    ipsis
    -0.09
     disproportion
    -0.09
    iji
    -0.09
    quina
    -0.09
    chte
    -0.09
     reinterpret
    -0.09
     slate
    -0.09
    alah
    -0.09
    POSITIVE LOGITS
     categor
    0.38
     categorized
    0.37
     grouped
    0.37
     categories
    0.34
     alphabetical
    0.34
     organized
    0.33
     grouping
    0.32
     organised
    0.29
     sorted
    0.28
     divided
    0.26
    Activations Density 1.169%

    No Known Activations