© 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. 28561
    Prev
    Next
    INDEX
    Explanations

    dates in numerical format

    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
    lush
    -0.11
     Marino
    -0.09
     sorte
    -0.09
     Gecko
    -0.09
     Halifax
    -0.08
     subst
    -0.08
    noinspection
    -0.08
     vient
    -0.08
    mue
    -0.08
     constit
    -0.08
    POSITIVE LOGITS
     polic
    0.10
     Prism
    0.09
     Dayton
    0.09
     Emerson
    0.09
     Lum
    0.09
     Zig
    0.08
     Pelosi
    0.08
    eler
    0.08
     stap
    0.08
     Cub
    0.08
    Activations Density 3.013%

    No Known Activations