© 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. 27960
    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
     admittedly
    -0.10
    _pot
    -0.10
     Gin
    -0.09
     dangerously
    -0.09
     Ham
    -0.09
    ÙĪر
    -0.09
    ulan
    -0.09
     sadly
    -0.08
     ers
    -0.08
    æ±
    -0.08
    POSITIVE LOGITS
    bserv
    0.10
    avo
    0.09
    uft
    0.09
    ensis
    0.09
    adow
    0.09
     Champ
    0.09
     molest
    0.09
    Curve
    0.09
     Weaver
    0.09
     interiors
    0.09
    Activations Density 0.000%

    No Known Activations