© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5322
    Prev
    Next
    INDEX
    Explanations

    passing time

    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
     informat
    -0.10
     persisted
    -0.10
    iam
    -0.10
     lingering
    -0.10
     superf
    -0.10
     dis
    -0.10
     temporarily
    -0.09
     persists
    -0.09
    anel
    -0.09
     Uns
    -0.09
    POSITIVE LOGITS
     wherein
    0.10
     trace
    0.09
    redis
    0.09
     before
    0.08
    ruz
    0.08
     Jacqueline
    0.08
    enes
    0.08
     sign
    0.08
     unnoticed
    0.07
     devoted
    0.07
    Activations Density 0.009%

    No Known Activations