© 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. 111716
    Prev
    Next
    INDEX
    Explanations

    Âł urls

    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
    745
    -0.09
     Command
    -0.08
     worthy
    -0.08
     Installed
    -0.08
     rig
    -0.08
     Hugo
    -0.08
     Lyn
    -0.08
     balance
    -0.08
     apparently
    -0.08
     Ost
    -0.08
    POSITIVE LOGITS
    forgot
    0.10
    sher
    0.10
    icos
    0.10
     homem
    0.09
    worked
    0.09
     Coupon
    0.09
    illary
    0.09
    aned
    0.09
     redes
    0.09
     surv
    0.09
    Activations Density 0.004%

    No Known Activations