© 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. 8040
    Prev
    Next
    INDEX
    Explanations

    pik-, ak-, jak-, ik-, bak- prefixes

    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
    aÄĩ
    -0.14
    a
    -0.13
    ey
    -0.13
    eil
    -0.13
    een
    -0.12
    ez
    -0.12
    ej
    -0.12
    aed
    -0.12
    est
    -0.11
    aad
    -0.11
    POSITIVE LOGITS
    ker
    0.16
    kers
    0.12
    ky
    0.11
    kel
    0.11
    king
    0.11
    ewood
    0.10
    KER
    0.10
    ka
    0.10
    ken
    0.09
    kle
    0.09
    Activations Density 0.138%

    No Known Activations