© 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. 90956
    Prev
    Next
    INDEX
    Explanations

    Things I've learned

    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
     Wonderland
    -0.09
     prom
    -0.09
    619
    -0.09
     promotion
    -0.09
     Slam
    -0.08
     predic
    -0.08
     relevant
    -0.08
     Kahn
    -0.08
    ll
    -0.08
     promot
    -0.08
    POSITIVE LOGITS
     learned
    0.13
     ~~
    0.11
     Learned
    0.11
     unexpectedly
    0.11
     learnt
    0.10
     NEVER
    0.10
    exas
    0.10
    nos
    0.10
    uti
    0.10
     irrit
    0.10
    Activations Density 0.098%

    No Known Activations