© 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. 17825
    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
     warrants
    -0.09
     your
    -0.09
    your
    -0.08
    adar
    -0.08
    este
    -0.08
    NECT
    -0.08
    )c
    -0.08
     prompts
    -0.08
    .decode
    -0.08
     MM
    -0.08
    POSITIVE LOGITS
     herself
    0.14
    .She
    0.11
    ensa
    0.11
     Magical
    0.10
     she
    0.10
    å¥
    0.10
     successes
    0.10
    Her
    0.09
    -city
    0.09
    She
    0.09
    Activations Density 0.000%

    No Known Activations