© 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. 113178
    Prev
    Next
    INDEX
    Explanations

    website, computer, and cookies

    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
    uling
    -0.10
    uggy
    -0.10
    unda
    -0.09
     seedu
    -0.09
    Ñĥн
    -0.09
     methodology
    -0.09
    zik
    -0.09
     improvised
    -0.09
     poss
    -0.09
     hor
    -0.09
    POSITIVE LOGITS
     affairs
    0.19
     finances
    0.15
     Affairs
    0.13
     portfolios
    0.12
     affair
    0.11
     expectations
    0.11
     risks
    0.11
     scarce
    0.11
     hedge
    0.11
     relationships
    0.11
    Activations Density 0.301%

    No Known Activations