© 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. 25319
    Prev
    Next
    INDEX
    Explanations

    best / trustworthy / reliably

    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
     Perry
    -0.10
     Birch
    -0.09
     alternate
    -0.09
     carefully
    -0.09
     Salv
    -0.08
    DAC
    -0.08
    ecs
    -0.08
     Famil
    -0.08
     approximate
    -0.08
     disposition
    -0.08
    POSITIVE LOGITS
     lest
    0.13
     best
    0.13
    best
    0.11
     truly
    0.11
     BEST
    0.11
     Parr
    0.10
     actually
    0.10
     trustworthy
    0.10
     reliably
    0.10
    (best
    0.10
    Activations Density 0.151%

    No Known Activations