© 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. 112716
    Prev
    Next
    INDEX
    Explanations

    following conjunctions or punctuation

    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
     therefore
    -0.14
     Franken
    -0.12
     consequently
    -0.12
    Therefore
    -0.11
    731
    -0.11
     Pace
    -0.11
     pace
    -0.11
    ieg
    -0.10
    writes
    -0.10
    ään
    -0.10
    POSITIVE LOGITS
    eri
    0.09
     ordin
    0.08
    Ord
    0.07
     cui
    0.07
     smaller
    0.07
     babys
    0.07
     Ord
    0.07
     lif
    0.07
     siz
    0.07
     gle
    0.07
    Activations Density 0.021%

    No Known Activations