© 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. 47275
    Prev
    Next
    INDEX
    Explanations

    want to view

    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
    opi
    -0.10
     Insp
    -0.09
    ounce
    -0.09
    starter
    -0.09
    upy
    -0.09
    opc
    -0.09
    essler
    -0.09
     copied
    -0.08
    ody
    -0.08
    Copy
    -0.08
    POSITIVE LOGITS
     filtering
    0.15
     filt
    0.14
     filter
    0.14
     filters
    0.14
     filtro
    0.12
     Filters
    0.12
     viewing
    0.11
     filtered
    0.11
     filtr
    0.11
    .filter
    0.11
    Activations Density 0.013%

    No Known Activations