© 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. 13903
    Prev
    Next
    INDEX
    Explanations

    gonna, wanna, gotta followed by verbs

    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
    cribe
    -0.10
    uran
    -0.10
    lee
    -0.10
    lys
    -0.10
    work
    -0.09
    shore
    -0.09
    LY
    -0.09
    fully
    -0.09
    wich
    -0.09
    clusions
    -0.09
    POSITIVE LOGITS
    '
    0.14
    ’
    0.13
    ogh
    0.12
    -sort
    0.10
    edu
    0.09
    istory
    0.09
    aton
    0.09
     be
    0.09
    erer
    0.08
    hell
    0.08
    Activations Density 0.013%

    No Known Activations