© 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. 34157
    Prev
    Next
    INDEX
    Explanations

    chained, tape, coupled, seated

    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
     Barker
    -0.10
     Heading
    -0.09
     Tape
    -0.09
     Leben
    -0.08
     Fasc
    -0.08
     nop
    -0.08
    ban
    -0.08
    far
    -0.08
    tape
    -0.08
     lords
    -0.08
    POSITIVE LOGITS
     attachment
    0.12
     chained
    0.10
     beside
    0.10
     wall
    0.10
     Washing
    0.10
    wc
    0.10
     gradient
    0.10
    shr
    0.09
     pillar
    0.09
     mural
    0.09
    Activations Density 0.015%

    No Known Activations