© 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. 31150
    Prev
    Next
    INDEX
    Explanations

    report an issue or suspicious activity

    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
     interrog
    -0.10
     wrath
    -0.10
    ubby
    -0.10
    ~/
    -0.09
    agli
    -0.09
     scrut
    -0.09
     bib
    -0.09
     Cabr
    -0.09
    ailing
    -0.09
    cl
    -0.09
    POSITIVE LOGITS
     BUG
    0.12
     bugs
    0.12
     suspicious
    0.11
     anonymously
    0.11
     sighting
    0.11
     suspected
    0.10
     someone
    0.10
     bug
    0.10
     sightings
    0.10
     activity
    0.09
    Activations Density 0.021%

    No Known Activations