© 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. 7955
    Prev
    Next
    INDEX
    Explanations

    don't get me wrong / started

    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
     anybody
    -0.11
     Marina
    -0.11
    inct
    -0.10
    odon
    -0.10
    -Ta
    -0.10
    inson
    -0.10
    addock
    -0.10
     practically
    -0.10
    ekt
    -0.10
    inya
    -0.10
    POSITIVE LOGITS
    ahas
    0.08
     wrong
    0.08
    /ca
    0.08
     WRONG
    0.08
    ulong
    0.08
     intercepted
    0.08
    okus
    0.08
     whipping
    0.08
     rever
    0.08
     modal
    0.08
    Activations Density 0.001%

    No Known Activations