© 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. 112466
    Prev
    Next
    INDEX
    Explanations

    after articles and prepositions

    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
     Ars
    -0.10
    ffa
    -0.10
     fragile
    -0.10
     debtor
    -0.10
    uf
    -0.09
    entr
    -0.09
     lodged
    -0.09
    targets
    -0.09
     frail
    -0.09
    677
    -0.09
    POSITIVE LOGITS
    jon
    0.10
    uro
    0.10
     whoever
    0.10
     strangers
    0.09
    knife
    0.09
     brink
    0.09
     him
    0.09
     stranger
    0.09
     hands
    0.09
    alah
    0.09
    Activations Density 0.084%

    No Known Activations