© 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. 50764
    Prev
    Next
    INDEX
    Explanations

    variety of, diversity of

    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
    ças
    -0.10
    agram
    -0.10
    urd
    -0.10
    /body
    -0.10
    ordo
    -0.10
    inery
    -0.10
     compat
    -0.09
    ToPoint
    -0.09
     Isa
    -0.09
    lege
    -0.09
    POSITIVE LOGITS
    /div
    0.15
    /options
    0.14
    /var
    0.12
     offered
    0.11
    iversity
    0.11
     breadth
    0.10
     diversity
    0.10
     afforded
    0.10
     Holl
    0.10
     within
    0.10
    Activations Density 0.085%

    No Known Activations