© 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. 92629
    Prev
    Next
    INDEX
    Explanations

    without avoiding

    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
    aze
    -0.11
     perfectly
    -0.10
     desi
    -0.10
     perfection
    -0.10
     perfected
    -0.09
     finely
    -0.09
     dai
    -0.09
    交
    -0.09
     Feinstein
    -0.09
    ALA
    -0.09
    POSITIVE LOGITS
     resort
    0.16
     seeming
    0.16
     risk
    0.15
     risking
    0.15
     Risk
    0.13
     sounding
    0.13
     outright
    0.13
     obvious
    0.13
    risk
    0.13
     Resort
    0.12
    Activations Density 0.047%

    No Known Activations