© 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. 18712
    Prev
    Next
    INDEX
    Explanations

    mang or marsh names

    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
    cial
    -0.11
    oins
    -0.10
    erin
    -0.10
    fois
    -0.10
    iren
    -0.10
     pare
    -0.10
    etes
    -0.10
    modes
    -0.10
    esi
    -0.10
     Autom
    -0.10
    POSITIVE LOGITS
    rove
    0.11
     mang
    0.09
    udad
    0.09
    IFn
    0.08
     Tur
    0.08
     larg
    0.08
    gro
    0.08
    olds
    0.07
     Bren
    0.07
    ahas
    0.07
    Activations Density 0.031%

    No Known Activations