© 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. 25185
    Prev
    Next
    INDEX
    Explanations

    part, parted, part-Native, part-Native American

    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
    htags
    -0.09
    aneous
    -0.07
    anz
    -0.07
    ument
    -0.07
    olate
    -0.07
    Ø°
    -0.07
    ly
    -0.07
    store
    -0.06
    UMENT
    -0.06
    lish
    -0.06
    POSITIVE LOGITS
     Barker
    0.15
    ially
    0.15
     pref
    0.14
     parted
    0.14
    /part
    0.13
    esp
    0.13
    ing
    0.13
     XIII
    0.12
    iene
    0.12
    icular
    0.12
    Activations Density 0.010%

    No Known Activations