© 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. 117368
    Prev
    Next
    INDEX
    Explanations

    for the first time

    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
    ober
    -0.11
    atr
    -0.10
    igue
    -0.10
    toList
    -0.10
    kr
    -0.10
    idon
    -0.10
    ures
    -0.10
    439
    -0.09
    jid
    -0.09
    urar
    -0.09
    POSITIVE LOGITS
     finally
    0.38
     unprecedented
    0.33
    finally
    0.30
     first
    0.26
     ì²ĺ
    0.25
     Finally
    0.23
    Finally
    0.22
     firstly
    0.21
    第
    0.21
    first
    0.20
    Activations Density 2.025%

    No Known Activations