© 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. 29261
    Prev
    Next
    INDEX
    Explanations

    summary and conclusion parts

    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
     Petro
    -0.09
     invalidated
    -0.08
     near
    -0.08
    olders
    -0.08
     "?"
    -0.08
    arak
    -0.08
    è´
    -0.08
     situ
    -0.07
    velle
    -0.07
    roc
    -0.07
    POSITIVE LOGITS
     Thoughts
    0.24
     thoughts
    0.21
     Wrap
    0.19
     Conclusion
    0.19
     wrap
    0.18
     conclusion
    0.17
    Conclusion
    0.16
     verdict
    0.16
     Bottom
    0.15
     Take
    0.15
    Activations Density 0.235%

    No Known Activations