© 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. 50566
    Prev
    Next
    INDEX
    Explanations

    scattered distribution

    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
    oret
    -0.11
    out
    -0.10
    estr
    -0.10
    alties
    -0.09
    inal
    -0.09
    pector
    -0.09
    gether
    -0.09
     Junk
    -0.09
    ugin
    -0.09
    umber
    -0.09
    POSITIVE LOGITS
    ting
    0.12
    tu
    0.11
    work
    0.11
    ingly
    0.10
    ViewItem
    0.10
    geist
    0.09
    tle
    0.09
    rell
    0.09
    lie
    0.09
    geo
    0.09
    Activations Density 0.076%

    No Known Activations