© 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. 92158
    Prev
    Next
    INDEX
    Explanations

    etc

    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
     repl
    -0.10
     replay
    -0.09
    rome
    -0.09
    SAT
    -0.09
    Clin
    -0.09
    oodle
    -0.09
    errat
    -0.09
    zee
    -0.08
    rame
    -0.08
    erson
    -0.08
    POSITIVE LOGITS
     miscellaneous
    0.16
     Miscellaneous
    0.13
    Misc
    0.09
    _misc
    0.09
     misc
    0.09
    misc
    0.09
     +/-
    0.08
     etc
    0.08
     Bust
    0.08
     <=>
    0.08
    Activations Density 1.019%

    No Known Activations