© 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. 33950
    Prev
    Next
    INDEX
    Explanations

    timestamps and version control diffs

    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
    Negative Logits
     wollte
    -0.08
    ض
    -0.08
    .newInstance
    -0.08
    Trial
    -0.08
    encia
    -0.08
    Tenant
    -0.08
     prolonged
    -0.08
     Rug
    -0.08
     condensed
    -0.08
     bumps
    -0.08
    POSITIVE LOGITS
    00
    0.16
    01
    0.11
    08
    0.10
    09
    0.10
    03
    0.10
    07
    0.10
    04
    0.10
    05
    0.10
    ple
    0.10
    aims
    0.10
    Activations Density 0.059%

    No Known Activations