© 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. 117380
    Prev
    Next
    INDEX
    Explanations

    look and feel quality

    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
     indis
    -0.09
     plunge
    -0.09
    Interrupt
    -0.08
    ucker
    -0.08
    Returned
    -0.08
     routines
    -0.08
     Piper
    -0.08
    preserve
    -0.08
     undesirable
    -0.08
     prelim
    -0.08
    POSITIVE LOGITS
    ndo
    0.10
    iw
    0.10
    adows
    0.09
    .um
    0.09
     fragile
    0.09
     Mun
    0.09
    frag
    0.09
     similar
    0.09
     jewel
    0.09
     Jon
    0.09
    Activations Density 0.014%

    No Known Activations