© 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. 114426
    Prev
    Next
    INDEX
    Explanations

    XlsxWriter

    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
    &S
    -0.11
     delegated
    -0.09
     runaway
    -0.09
     receptive
    -0.09
    dre
    -0.09
    ourn
    -0.09
    bilt
    -0.09
    marvin
    -0.09
    /head
    -0.08
    istica
    -0.08
    POSITIVE LOGITS
    âĢĮ
    0.12
    eral
    0.10
     latter
    0.09
     stunt
    0.09
    osate
    0.09
     Tara
    0.09
    à§į
    0.08
     Stacy
    0.08
     thrust
    0.08
     ad
    0.08
    Activations Density 0.002%

    No Known Activations