© 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. 117247
    Prev
    Next
    INDEX
    Explanations

    community, versions, profiles, objectives

    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
     subst
    -0.10
    backs
    -0.09
     Copp
    -0.08
     Levine
    -0.08
     contentType
    -0.08
     kn
    -0.08
    /Foundation
    -0.08
     dime
    -0.08
     cst
    -0.08
    yntax
    -0.08
    POSITIVE LOGITS
    chal
    0.10
    /pop
    0.09
    isma
    0.09
     Dew
    0.09
    AGO
    0.09
     Conn
    0.09
    chnitt
    0.09
     distrust
    0.09
    anych
    0.09
    cio
    0.09
    Activations Density 0.010%

    No Known Activations