© 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. 45976
    Prev
    Next
    INDEX
    Explanations

    place or proper noun descriptor

    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
     Hoch
    -0.12
     sal
    -0.11
     Sal
    -0.11
    (()=>
    -0.10
     Infer
    -0.10
    sal
    -0.10
    uel
    -0.09
     rel
    -0.09
     pertinent
    -0.09
    attern
    -0.09
    POSITIVE LOGITS
    ensch
    0.09
    /,↵
    0.08
     Leak
    0.08
    earch
    0.08
     leak
    0.08
    ulist
    0.08
    orum
    0.08
    amac
    0.07
     sund
    0.07
    lash
    0.07
    Activations Density 0.191%

    No Known Activations