© 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. 46398
    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
     affirm
    -0.08
     requis
    -0.08
     unf
    -0.08
     me
    -0.08
    Grant
    -0.07
     needless
    -0.07
     Grant
    -0.07
     HQ
    -0.07
    æĪij
    -0.07
     prefab
    -0.07
    POSITIVE LOGITS
    utar
    0.11
    ILT
    0.10
    VRT
    0.10
     Pike
    0.10
     resisting
    0.10
    ulle
    0.10
     Worth
    0.10
    opes
    0.10
    Overlay
    0.09
    rtle
    0.09
    Activations Density 0.000%

    No Known Activations