© 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. 5758
    Prev
    Next
    INDEX
    Explanations

    filtering and narrowing searches

    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
    abad
    -0.08
    outh
    -0.08
     Holden
    -0.08
     Glow
    -0.08
    aman
    -0.07
     kle
    -0.07
     Excell
    -0.07
     Trip
    -0.07
     Tee
    -0.07
     Detect
    -0.07
    POSITIVE LOGITS
     Filters
    0.12
    Filters
    0.11
    htags
    0.11
     narrower
    0.11
    arti
    0.11
     Filtering
    0.11
    elib
    0.11
     facet
    0.11
     filters
    0.11
     swe
    0.11
    Activations Density 0.004%

    No Known Activations