© 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. 117529
    Prev
    Next
    INDEX
    Explanations

    J, V, RY, Mr, al, T, Bar, Jer

    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
     [...]↵↵
    -0.09
    amat
    -0.09
    ‘s
    -0.08
    rtype
    -0.08
     Gio
    -0.07
    redi
    -0.07
    ippi
    -0.07
    edin
    -0.07
    unk
    -0.07
    azon
    -0.07
    POSITIVE LOGITS
    eeee
    0.13
    !
    0.13
    oooooooo
    0.13
     Fucking
    0.12
    ?"↵↵↵↵
    0.12
     fucking
    0.12
    oooo
    0.12
    aaaa
    0.12
    ieee
    0.12
     dear
    0.12
    Activations Density 0.015%

    No Known Activations