© 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. 45991
    Prev
    Next
    INDEX
    Explanations

    answers and replies

    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
     resend
    -0.11
    ker
    -0.10
    upon
    -0.10
     Pays
    -0.09
     payable
    -0.09
     Jur
    -0.09
     Proceed
    -0.09
     writeln
    -0.08
     Teh
    -0.08
     Kle
    -0.08
    POSITIVE LOGITS
     him
    0.14
     indirectly
    0.13
     aloud
    0.13
     intellig
    0.11
     indirect
    0.11
     differently
    0.11
     verbally
    0.10
    708
    0.10
     negatively
    0.10
    elman
    0.10
    Activations Density 0.014%

    No Known Activations