© 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. 34155
    Prev
    Next
    INDEX
    Explanations

    put it

    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
     Chall
    -0.09
    dd
    -0.08
     glow
    -0.07
     climb
    -0.07
     Toledo
    -0.07
     inv
    -0.07
     familiarity
    -0.07
    udder
    -0.07
     tw
    -0.07
     immedi
    -0.07
    POSITIVE LOGITS
     aside
    0.15
    aside
    0.13
    semb
    0.13
     MASK
    0.12
     Forward
    0.12
     forward
    0.11
     emphasis
    0.11
     awake
    0.11
    ted
    0.11
    inz
    0.11
    Activations Density 0.124%

    No Known Activations