© 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. 34216
    Prev
    Next
    INDEX
    Explanations

    demonstrative pronouns or punctuation

    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
     )[
    -0.10
     Caval
    -0.10
    ause
    -0.10
    éc
    -0.10
     Latter
    -0.10
    oute
    -0.10
     dispos
    -0.10
     Reform
    -0.09
     cb
    -0.09
    afort
    -0.09
    POSITIVE LOGITS
     thats
    0.26
    -that
    0.24
    —that
    0.23
    That
    0.21
     That
    0.20
     THAT
    0.19
    .That
    0.18
    _that
    0.13
     according
    0.13
    these
    0.12
    Activations Density 0.295%

    No Known Activations