© 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. 14642
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure

    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
     Sk
    -0.07
     underlying
    -0.07
     sk
    -0.07
     blind
    -0.07
     foregoing
    -0.07
     âĨĴ↵↵
    -0.07
     obligatory
    -0.07
     sch
    -0.07
    Carthy
    -0.07
     &
    -0.07
    POSITIVE LOGITS
    zi
    0.12
     conclusion
    0.11
    ###
    0.11
    Expanded
    0.11
     ens
    0.11
     ðŁĴ
    0.11
     Bulk
    0.11
     Conclusion
    0.11
     ðŁ
    0.11
     Uri
    0.11
    Activations Density 0.104%

    No Known Activations