© 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. 45964
    Prev
    Next
    INDEX
    Explanations

    questions starting with Why or What

    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
     premises
    -0.09
     camer
    -0.08
     meanwhile
    -0.08
     sw
    -0.07
     flag
    -0.07
     tele
    -0.07
     squat
    -0.07
     Zah
    -0.07
     selfie
    -0.07
     Hew
    -0.07
    POSITIVE LOGITS
     why
    0.42
     Why
    0.40
    why
    0.37
    Why
    0.36
     WHY
    0.35
     pourquoi
    0.27
    "Why
    0.26
     whats
    0.17
     What
    0.16
    ä½ķ
    0.15
    Activations Density 0.099%

    No Known Activations