© 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. 6507
    Prev
    Next
    INDEX
    Explanations

    not just but

    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
     merely
    -0.15
     simply
    -0.14
     just
    -0.11
     Simply
    -0.11
    Simply
    -0.10
     simplement
    -0.09
    :↵↵↵↵
    -0.09
     ambush
    -0.09
     mere
    -0.08
    toc
    -0.08
    POSITIVE LOGITS
    /Dk
    0.11
     reactive
    0.10
     Trend
    0.10
     Maher
    0.10
    IFI
    0.09
    isl
    0.09
    iert
    0.09
     Spa
    0.09
     ISI
    0.09
     interv
    0.09
    Activations Density 0.001%

    No Known Activations