© 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. 32194
    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
    ENO
    -0.11
     Dob
    -0.08
     unfinished
    -0.07
     Herc
    -0.07
     arrangement
    -0.07
    cade
    -0.07
     Olson
    -0.07
     Arr
    -0.07
     arrangements
    -0.07
    .depend
    -0.07
    POSITIVE LOGITS
     hoping
    0.14
     exhaustive
    0.12
     só
    0.11
     deterministic
    0.11
     tabs
    0.11
    ozo
    0.11
     extensively
    0.11
     intrigued
    0.10
     intrig
    0.10
     hoped
    0.10
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.