© 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. 3693
    Prev
    Next
    INDEX
    Explanations

    desire or condition leads to outcome

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ugo
    -0.12
    avis
    -0.10
    osi
    -0.10
    liv
    -0.10
    lam
    -0.10
    ey
    -0.09
    odor
    -0.09
    illo
    -0.09
    377
    -0.09
     SAC
    -0.09
    POSITIVE LOGITS
     outweigh
    0.16
     arises
    0.16
     motivate
    0.13
     stems
    0.13
     motiv
    0.13
     drove
    0.13
     coupled
    0.13
     ming
    0.13
     tempered
    0.12
     arose
    0.12
    Activations Density 0.205%

    No Known Activations