© 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. 49554
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives and nouns

    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
    akan
    -0.11
     sometime
    -0.10
    ibe
    -0.10
    ?"↵↵↵↵
    -0.10
    endif
    -0.10
    vang
    -0.10
     Messiah
    -0.10
     mentre
    -0.10
     cryst
    -0.10
    rier
    -0.09
    POSITIVE LOGITS
     for
    0.13
    ously
    0.11
     if
    0.11
     even
    0.11
     anyone
    0.11
     when
    0.10
    ä»»
    0.10
     anybody
    0.09
     considering
    0.09
    for
    0.09
    Activations Density 0.186%

    No Known Activations