© 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. 33883
    Prev
    Next
    INDEX
    Explanations

    decrease, end, or negation

    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
     Petty
    -0.09
     cond
    -0.09
     Gy
    -0.09
    Cha
    -0.09
     Parsons
    -0.09
     cha
    -0.08
     boosts
    -0.08
     statically
    -0.08
     pause
    -0.08
     Cha
    -0.08
    POSITIVE LOGITS
     powerless
    0.12
     collapsing
    0.11
    .opensource
    0.11
     freeing
    0.11
     releasing
    0.10
     worthless
    0.10
     pang
    0.10
     frustr
    0.10
     extrad
    0.10
     falling
    0.10
    Activations Density 0.014%

    No Known Activations