© 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. 49761
    Prev
    Next
    INDEX
    Explanations

    MIT License

    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
    anzi
    -0.15
    sx
    -0.12
    rei
    -0.12
     xpos
    -0.12
     jsx
    -0.11
    aad
    -0.11
    /im
    -0.11
    hints
    -0.11
     whitelist
    -0.11
     Erotic
    -0.11
    POSITIVE LOGITS
    erta
    0.08
     ag
    0.07
    ecture
    0.07
     nond
    0.06
     Cumberland
    0.06
    erea
    0.06
    entar
    0.06
     Aurora
    0.06
     Abbott
    0.06
    sons
    0.06
    Activations Density 0.001%

    No Known Activations