© 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. 14225
    Prev
    Next
    INDEX
    Explanations

    assumption that

    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
     arguably
    -0.16
     unexpectedly
    -0.12
     neither
    -0.11
     reportedly
    -0.10
     surprisingly
    -0.10
     often
    -0.10
     probably
    -0.09
    Depending
    -0.09
     Depending
    -0.09
     quite
    -0.09
    POSITIVE LOGITS
     somehow
    0.31
     necessarily
    0.23
     automatically
    0.22
     magically
    0.22
     Somehow
    0.18
     Automatically
    0.17
     mirac
    0.16
     carte
    0.14
     Calder
    0.13
    ecessarily
    0.13
    Activations Density 0.228%

    No Known Activations