© 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. 15462
    Prev
    Next
    INDEX
    Explanations

    numbers in parentheses

    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
     mist
    -0.10
     discourse
    -0.08
     Bush
    -0.08
    ).(
    -0.08
     Gem
    -0.08
    loff
    -0.08
     commonplace
    -0.08
     Merc
    -0.08
     Heads
    -0.07
    serial
    -0.07
    POSITIVE LOGITS
    )/
    0.12
    }catch
    0.12
    kul
    0.12
     plac
    0.11
     smugg
    0.11
    orge
    0.11
     Mull
    0.10
     swo
    0.10
    cil
    0.10
     rolling
    0.10
    Activations Density 1.171%

    No Known Activations