© 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. 18651
    Prev
    Next
    INDEX
    Explanations

    numbers and bodies

    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
     sideways
    -0.10
     flakes
    -0.10
     sid
    -0.10
     dispersed
    -0.10
     Lans
    -0.09
     downhill
    -0.09
     pall
    -0.09
     whip
    -0.09
     Waves
    -0.09
    AQ
    -0.09
    POSITIVE LOGITS
     hips
    0.14
     herself
    0.12
     torso
    0.12
     himself
    0.10
    аÑĤÑĮÑģÑı
    0.10
     Yourself
    0.10
     myself
    0.10
     yourself
    0.10
     slightly
    0.09
    neck
    0.09
    Activations Density 0.005%

    No Known Activations