© 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. 26276
    Prev
    Next
    INDEX
    Explanations

    Java public common

    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
     autoload
    -0.10
     diversity
    -0.10
    blocking
    -0.10
     extra
    -0.09
     fulfil
    -0.09
    elsif
    -0.09
     Cand
    -0.09
     sustainability
    -0.09
     blocking
    -0.08
    abil
    -0.08
    POSITIVE LOGITS
    elli
    0.10
     dik
    0.09
    illus
    0.09
     bust
    0.09
    inion
    0.09
     slower
    0.09
    èIJ
    0.09
    acl
    0.08
    oven
    0.08
    actus
    0.08
    Activations Density 0.008%

    No Known Activations