© 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. 30240
    Prev
    Next
    INDEX
    Explanations

    revealed, discovered, apparently

    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
    imo
    -0.10
    otti
    -0.09
     Visible
    -0.09
     takeover
    -0.09
    ehr
    -0.09
     ÑĥÑģп
    -0.08
     surely
    -0.08
    enk
    -0.08
    umpt
    -0.08
     Hon
    -0.08
    POSITIVE LOGITS
     Turns
    0.48
     turns
    0.35
     revealed
    0.35
     revelation
    0.32
     Apparently
    0.32
     apparently
    0.31
     discovered
    0.30
    Apparently
    0.29
     reveal
    0.28
     revelations
    0.28
    Activations Density 0.456%

    No Known Activations