© 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. 14135
    Prev
    Next
    INDEX
    Explanations

    infinitives or verb conjugations

    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
    printStats
    -0.12
    >manual
    -0.12
    _tE
    -0.11
    	DBG
    -0.11
     pestic
    -0.11
     contemplated
    -0.11
     '../../../../../
    -0.11
    prestashop
    -0.11
    ilst
    -0.10
     "...
    -0.10
    POSITIVE LOGITS
     âĢ¦
    0.12
     [âĢ¦]
    0.11
    ”
    0.11
     [âĢ¦
    0.11
    »
    0.10
    your
    0.10
     ___
    0.09
    ðŁ
    0.09
    ÂŃ
    0.09
    .”
    0.09
    Activations Density 0.218%

    No Known Activations