© 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. 46303
    Prev
    Next
    INDEX
    Explanations

    operation principle

    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
    ocha
    -0.09
     discriminator
    -0.09
     Spice
    -0.09
     fore
    -0.08
     Trev
    -0.08
     motiv
    -0.08
     Occasionally
    -0.08
     debugging
    -0.08
    gate
    -0.08
     informal
    -0.08
    POSITIVE LOGITS
     relies
    0.23
     mechanism
    0.22
     rely
    0.20
     Mechan
    0.20
     principle
    0.19
     mechanisms
    0.19
     relying
    0.18
     exploiting
    0.18
     mechanically
    0.18
     Principle
    0.17
    Activations Density 2.986%

    No Known Activations