© 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. 117099
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Eden
    -0.08
     innocence
    -0.07
    uner
    -0.07
     accompany
    -0.07
    ogg
    -0.07
     compliment
    -0.07
    lyn
    -0.07
     innocent
    -0.07
     contents
    -0.07
     Bash
    -0.07
    POSITIVE LOGITS
    alyzed
    0.11
    оÑĩ
    0.11
    athe
    0.11
    Signup
    0.11
    uste
    0.11
     Choices
    0.11
    essler
    0.11
     watershed
    0.10
     Diy
    0.10
    /ws
    0.10
    Activations Density 0.000%

    No Known Activations