© 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. 28802
    Prev
    Next
    INDEX
    Explanations

    become increasingly common

    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
     awake
    -0.10
     PST
    -0.10
     scratch
    -0.10
    /sn
    -0.10
     Carroll
    -0.10
     ath
    -0.10
     pes
    -0.09
    .bi
    -0.09
    /bl
    -0.09
     mad
    -0.09
    POSITIVE LOGITS
     synonymous
    0.16
     increasingly
    0.14
     synonym
    0.12
     shorthand
    0.11
     part
    0.11
     indispensable
    0.11
     integral
    0.09
     an
    0.09
     progressively
    0.09
     regarded
    0.09
    Activations Density 0.061%

    No Known Activations