© 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. 8255
    Prev
    Next
    INDEX
    Explanations

    president, pastor, rabbi

    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
    pile
    -0.09
    enco
    -0.08
     Cair
    -0.08
     tones
    -0.08
     Podesta
    -0.08
     Feld
    -0.08
     Cowboys
    -0.08
     Pence
    -0.08
     Werk
    -0.08
    ihar
    -0.07
    POSITIVE LOGITS
     X
    0.13
     XXX
    0.13
     XYZ
    0.13
     Whats
    0.12
    -elect
    0.12
     xxx
    0.11
     xyz
    0.11
     XY
    0.11
     XX
    0.10
    XXXX
    0.10
    Activations Density 0.329%

    No Known Activations