© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 17739
    Prev
    Next
    INDEX
    Explanations

    seed and breeding

    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
     trunk
    -0.11
     coke
    -0.10
     roku
    -0.10
     branches
    -0.10
    æŃ
    -0.10
    SCAN
    -0.10
     Coke
    -0.10
     sluggish
    -0.10
     Mines
    -0.09
    omat
    -0.09
    POSITIVE LOGITS
    Seed
    0.32
     Seed
    0.31
     seed
    0.31
     Seeds
    0.31
     seeds
    0.29
    seed
    0.25
    _seed
    0.23
    .seed
    0.20
     Seeder
    0.20
     seeding
    0.20
    Activations Density 0.524%

    No Known Activations