© 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. 15170
    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
     hos
    -0.10
     vex
    -0.09
     vac
    -0.09
     DBG
    -0.09
     dov
    -0.09
    alon
    -0.09
     bona
    -0.08
     Sh
    -0.08
    efs
    -0.08
     Gill
    -0.08
    POSITIVE LOGITS
    å±Ģ
    0.10
    rack
    0.09
    oba
    0.09
    vie
    0.09
    tie
    0.09
     categorical
    0.09
     Sutton
    0.08
    ’)
    0.08
     sizing
    0.08
    vil
    0.08
    Activations Density 0.000%

    No Known Activations