© 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. 15494
    Prev
    Next
    INDEX
    Explanations

    again, we

    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
    499
    -0.10
    /opt
    -0.10
    REL
    -0.10
     LOC
    -0.10
    aes
    -0.10
    uess
    -0.10
    spr
    -0.10
     bcm
    -0.09
     attic
    -0.09
     cleanly
    -0.09
    POSITIVE LOGITS
     silence
    0.12
     pause
    0.09
     waves
    0.09
    jian
    0.09
    ivre
    0.09
    !?
    0.08
     curiosity
    0.08
     darn
    0.08
     gunfire
    0.08
     she
    0.08
    Activations Density 0.004%

    No Known Activations