© 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. 116838
    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
     agenda
    -0.11
    yled
    -0.11
     whe
    -0.10
    otta
    -0.10
    ennen
    -0.10
    oor
    -0.10
     Agenda
    -0.10
     otherwise
    -0.10
     blessing
    -0.10
     presently
    -0.10
    POSITIVE LOGITS
    ichel
    0.11
    shire
    0.08
    azers
    0.08
     bal
    0.08
    mol
    0.07
    (getClass
    0.07
     ðŁĶ
    0.07
     Baxter
    0.07
    ande
    0.07
    åı¸
    0.07
    Activations Density 0.000%

    No Known Activations