© 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. 45992
    Prev
    Next
    INDEX
    Explanations

    Online trading, convenience, specialists

    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
     Kes
    -0.12
     Din
    -0.11
    uke
    -0.08
     stret
    -0.08
    HIR
    -0.08
     Masc
    -0.08
    ochen
    -0.07
     scrut
    -0.07
     OPS
    -0.07
     Crystal
    -0.07
    POSITIVE LOGITS
    ãģĵãĤĵ
    0.10
    adoras
    0.10
    nv
    0.10
     Convenience
    0.10
     prox
    0.10
     Buzz
    0.10
    AVING
    0.10
    uxtap
    0.10
     Basket
    0.10
     convenience
    0.10
    Activations Density 0.001%

    No Known Activations