© 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. 92633
    Prev
    Next
    INDEX
    Explanations

    actions of falling or slipping

    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
     interfering
    -0.12
    @Web
    -0.11
    rij
    -0.11
     warmly
    -0.10
     insured
    -0.10
    Nach
    -0.10
     interfer
    -0.10
    lien
    -0.10
    itti
    -0.10
     Roch
    -0.10
    POSITIVE LOGITS
    /run
    0.12
    /sl
    0.10
     backward
    0.10
     sprawling
    0.09
     backwards
    0.09
     casc
    0.08
    rog
    0.08
    orie
    0.08
    /star
    0.08
    onn
    0.08
    Activations Density 0.008%

    No Known Activations