© 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. 29602
    Prev
    Next
    INDEX
    Explanations

    bark, barking, barker

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ought
    -0.10
    fas
    -0.10
    vers
    -0.10
     unf
    -0.09
     verd
    -0.09
    azy
    -0.09
     lump
    -0.09
     gaz
    -0.09
    PARAM
    -0.09
    aze
    -0.09
    POSITIVE LOGITS
    itecture
    0.11
    illage
    0.11
     bark
    0.10
     Dag
    0.10
    chip
    0.10
    illon
    0.09
     orders
    0.09
    lotte
    0.09
    nowled
    0.09
     loudly
    0.09
    Activations Density 0.002%

    No Known Activations