© 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. 117314
    Prev
    Next
    INDEX
    Explanations

    the [comparative adjective]

    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
     prere
    -0.12
    DU
    -0.11
    /b
    -0.11
    &B
    -0.10
    obili
    -0.10
    ocl
    -0.10
     HM
    -0.10
     Dob
    -0.09
    avan
    -0.09
    bum
    -0.09
    POSITIVE LOGITS
     closer
    0.17
     harder
    0.17
     more
    0.17
     easier
    0.15
     quicker
    0.15
     farther
    0.14
     faster
    0.14
     better
    0.14
     fewer
    0.14
     louder
    0.13
    Activations Density 0.014%

    No Known Activations