© 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. 28413
    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
     l
    -0.09
     diaper
    -0.09
     lingering
    -0.09
    _te
    -0.09
     faint
    -0.08
     everywhere
    -0.08
     casts
    -0.07
     eens
    -0.07
     Pac
    -0.07
    arde
    -0.07
    POSITIVE LOGITS
     deliberate
    0.11
    edin
    0.11
    udent
    0.10
     deliberately
    0.10
    ordial
    0.10
    æĦı
    0.10
    stin
    0.10
     consenting
    0.09
    iske
    0.09
    utas
    0.09
    Activations Density 0.000%

    No Known Activations