© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31289
    Prev
    Next
    INDEX
    Explanations

    gives a

    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
    zos
    -0.11
    zer
    -0.11
    successfully
    -0.11
     readily
    -0.11
    ika
    -0.10
    hone
    -0.10
     happily
    -0.10
     indem
    -0.10
    aley
    -0.10
    istar
    -0.10
    POSITIVE LOGITS
     a
    0.10
     plenty
    0.08
     pastor
    0.07
     ($)
    0.07
     an
    0.07
     Pastor
    0.06
    rog
    0.06
     enough
    0.06
     [&
    0.06
    —the
    0.06
    Activations Density 0.258%

    No Known Activations