© 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. 25835
    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
     Roe
    -0.10
     Isis
    -0.07
    errs
    -0.07
    onde
    -0.07
    cri
    -0.07
    riel
    -0.07
     Child
    -0.06
    -r
    -0.06
    ruz
    -0.06
     gra
    -0.06
    POSITIVE LOGITS
     preferred
    0.13
    sten
    0.12
     permitted
    0.12
    ses
    0.11
    olib
    0.11
     beginnings
    0.11
     preferable
    0.11
    GEST
    0.11
    né
    0.11
     dbg
    0.11
    Activations Density 0.000%

    No Known Activations