© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 6511
    Prev
    Next
    INDEX
    Explanations

    moderation, balance, importance

    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
     Vict
    -0.10
    resco
    -0.10
     regret
    -0.10
    dda
    -0.10
    ropolitan
    -0.10
     technically
    -0.10
     scram
    -0.10
    NOW
    -0.10
     Neb
    -0.09
     amazingly
    -0.09
    POSITIVE LOGITS
     balance
    0.23
     moderate
    0.23
     occasional
    0.22
     moderation
    0.22
     balanced
    0.21
     Balance
    0.20
     reasonable
    0.20
     Moderate
    0.19
    Balance
    0.18
     Balanced
    0.17
    Activations Density 0.121%

    No Known Activations