© 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. 16474
    Prev
    Next
    INDEX
    Explanations

    laid out, fit for

    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
    âĢ
    -0.08
     properly
    -0.08
     comparative
    -0.07
     Jag
    -0.07
     ,
    -0.07
    “
    -0.06
    Ãł
    -0.06
     deeper
    -0.06
     effortlessly
    -0.06
     Kinder
    -0.06
    POSITIVE LOGITS
     abound
    0.16
    obl
    0.13
     fruition
    0.13
     recourse
    0.12
    sted
    0.12
    interop
    0.12
    anan
    0.12
    fare
    0.12
    oday
    0.12
    bor
    0.12
    Activations Density 0.302%

    No Known Activations