© 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. 30539
    Prev
    Next
    INDEX
    Explanations

    sending distributed content

    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
     remembered
    -0.09
     Saved
    -0.09
     rev
    -0.09
     recalled
    -0.09
     scri
    -0.09
     collections
    -0.09
     commemor
    -0.09
     reusable
    -0.08
     refactor
    -0.08
     retrieved
    -0.08
    POSITIVE LOGITS
     sent
    0.14
     anonymously
    0.13
     plaster
    0.13
     distributed
    0.13
    distributed
    0.13
     distribute
    0.12
     Distrib
    0.12
     blackmail
    0.12
     circulated
    0.11
    Sending
    0.11
    Activations Density 0.129%

    No Known Activations