© 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. 111625
    Prev
    Next
    INDEX
    Explanations

    solving their problems

    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
    Nib
    -0.09
    717
    -0.09
    ocz
    -0.09
    asion
    -0.08
    usch
    -0.08
    ied
    -0.08
    IED
    -0.08
    TRS
    -0.08
     fiercely
    -0.07
     lest
    -0.07
    POSITIVE LOGITS
     problems
    0.49
     troubles
    0.49
     woes
    0.44
     Problems
    0.43
    problems
    0.40
     worries
    0.40
     problem
    0.30
     Proble
    0.29
     problemas
    0.28
    /problems
    0.28
    Activations Density 0.111%

    No Known Activations