© 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. 16842
    Prev
    Next
    INDEX
    Explanations

    lists of items or descriptions

    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
    ...↵↵↵↵
    -0.11
    âĢ¦↵↵↵↵
    -0.09
     shy
    -0.09
    ippo
    -0.09
     therein
    -0.09
     PROT
    -0.09
    lsa
    -0.08
    ryn
    -0.08
    abra
    -0.08
    assi
    -0.08
    POSITIVE LOGITS
     finally
    0.14
     natürlich
    0.10
    /[
    0.10
    tera
    0.09
     hin
    0.09
    usters
    0.09
    isten
    0.09
    #+
    0.09
     Wolfe
    0.09
    MORE
    0.09
    Activations Density 0.283%

    No Known Activations