© 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. 25241
    Prev
    Next
    INDEX
    Explanations

    changes and instability

    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
    ots
    -0.09
     parallels
    -0.08
     extrapol
    -0.08
     withholding
    -0.08
     Everyday
    -0.08
     gated
    -0.08
     rusty
    -0.08
    illet
    -0.08
     asleep
    -0.08
     Patrol
    -0.08
    POSITIVE LOGITS
     successive
    0.34
     succession
    0.28
     transient
    0.27
     constantly
    0.22
     unstable
    0.21
     bounced
    0.21
     sequentially
    0.21
     fleeting
    0.21
     ephem
    0.20
     changing
    0.20
    Activations Density 0.540%

    No Known Activations