© 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. 87626
    Prev
    Next
    INDEX
    Explanations

    physical interaction or sensation

    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
     zeal
    -0.08
     nei
    -0.08
    /**↵↵
    -0.07
     kneeling
    -0.07
     handed
    -0.07
     pis
    -0.07
     staring
    -0.07
     ze
    -0.07
    ):-
    -0.07
    olla
    -0.07
    POSITIVE LOGITS
    udded
    0.11
     raw
    0.10
     bumps
    0.10
     Muse
    0.10
    elong
    0.10
     Mik
    0.10
     gated
    0.10
    ansa
    0.10
    ledged
    0.10
    mute
    0.10
    Activations Density 0.016%

    No Known Activations