© 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. 25305
    Prev
    Next
    INDEX
    Explanations

    should have / had

    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
     owed
    -0.15
    Ars
    -0.13
     owe
    -0.13
     Sark
    -0.12
     owes
    -0.11
     Arsenal
    -0.10
     barely
    -0.10
     promising
    -0.10
     wand
    -0.10
    eve
    -0.10
    POSITIVE LOGITS
     stayed
    0.16
     never
    0.14
     chose
    0.14
     heed
    0.14
     sooner
    0.13
     chosen
    0.13
    never
    0.12
     listened
    0.12
     aborted
    0.12
     stays
    0.11
    Activations Density 0.091%

    No Known Activations