© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 14124
    Prev
    Next
    INDEX
    Explanations

    does anyone/anybody/mean

    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
    Negative Logits
    ÅĽmy
    -0.12
    lege
    -0.09
     themselves
    -0.09
    yah
    -0.09
    Äĩi
    -0.09
    amon
    -0.08
    .contents
    -0.08
    ress
    -0.08
    ego
    -0.08
    onom
    -0.08
    POSITIVE LOGITS
    NotExist
    0.18
     exist
    0.13
     mean
    0.13
     anyone
    0.12
    mean
    0.12
    nty
    0.12
    nda
    0.12
     seem
    0.11
    n
    0.11
     anybody
    0.10
    Activations Density 0.142%

    No Known Activations