© 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. 15128
    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
    fty
    -0.11
     Bench
    -0.10
    asan
    -0.10
     markets
    -0.10
     Mam
    -0.10
    ingham
    -0.10
    /fs
    -0.10
    PMC
    -0.09
     Bear
    -0.09
     neutr
    -0.09
    POSITIVE LOGITS
    orie
    0.09
     cowork
    0.09
     molded
    0.09
     Miranda
    0.09
     fro
    0.08
    ters
    0.08
     POV
    0.08
    toy
    0.08
    dong
    0.08
    zell
    0.08
    Activations Density 0.000%

    No Known Activations