© 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. 8172
    Prev
    Next
    INDEX
    Explanations

    earn money or degrees

    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
     Rece
    -0.11
    gm
    -0.10
     Glad
    -0.10
    onis
    -0.10
     rampant
    -0.09
    aland
    -0.09
    timer
    -0.09
     linger
    -0.09
    pons
    -0.09
    teen
    -0.09
    POSITIVE LOGITS
    shaw
    0.15
     money
    0.14
    hardt
    0.14
    /save
    0.12
    esty
    0.12
    /pay
    0.11
    oming
    0.11
    money
    0.11
     Money
    0.10
     respect
    0.10
    Activations Density 0.025%

    No Known Activations