© 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. 14379
    Prev
    Next
    INDEX
    Explanations

    U.S. Court of Appeals Circuit

    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
     turned
    -0.18
     turning
    -0.17
     rear
    -0.15
     turn
    -0.15
     Turning
    -0.14
    turn
    -0.14
     turnaround
    -0.14
    Turning
    -0.14
     Turn
    -0.13
     behind
    -0.13
    POSITIVE LOGITS
    weg
    0.12
    æģ¯
    0.11
    dio
    0.11
     domic
    0.11
     converge
    0.11
    azu
    0.11
     pup
    0.11
    çIJ
    0.11
     rises
    0.11
    {@
    0.11
    Activations Density 0.030%

    No Known Activations