© 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. 29492
    Prev
    Next
    INDEX
    Explanations

    reviews, guides, applications, resources

    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
    ibu
    -0.11
    /change
    -0.10
     Cros
    -0.10
    ombs
    -0.10
    /page
    -0.09
    /content
    -0.09
    :?
    -0.09
     beige
    -0.09
     vice
    -0.09
     unintention
    -0.09
    POSITIVE LOGITS
    /Graphics
    0.10
     facility
    0.09
    otti
    0.08
     regs
    0.08
     Americas
    0.08
     incl
    0.08
     Alla
    0.08
     Scr
    0.08
     Alive
    0.08
     evolutionary
    0.08
    Activations Density 0.037%

    No Known Activations