© 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. 111469
    Prev
    Next
    INDEX
    Explanations

    reasons to

    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
     sandwich
    -0.08
    755
    -0.07
     Terry
    -0.07
    swer
    -0.06
     impact
    -0.06
    impact
    -0.06
     inp
    -0.06
    ugg
    -0.06
     tac
    -0.06
    aten
    -0.06
    POSITIVE LOGITS
     why
    0.21
    why
    0.19
     WHY
    0.18
    Why
    0.18
     Why
    0.17
     reasons
    0.16
     justify
    0.16
     Reasons
    0.16
     pourquoi
    0.15
     reason
    0.14
    Activations Density 0.143%

    No Known Activations