© 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. 92357
    Prev
    Next
    INDEX
    Explanations

    credit the

    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
     forgiven
    -0.10
     Worse
    -0.10
     TAS
    -0.10
    ilet
    -0.09
    —which
    -0.09
    clud
    -0.09
     bre
    -0.09
     owing
    -0.09
     comps
    -0.09
    iel
    -0.08
    POSITIVE LOGITS
     Makes
    0.16
     Gives
    0.15
    makes
    0.14
    Makes
    0.13
     Keeps
    0.12
     reminds
    0.12
     Helps
    0.12
     Means
    0.12
    means
    0.12
     makes
    0.12
    Activations Density 0.079%

    No Known Activations