© 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. 26561
    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
     Wilderness
    -0.11
    neh
    -0.11
    ivr
    -0.10
     conscience
    -0.10
     Roc
    -0.10
     wilderness
    -0.10
    iker
    -0.10
    Ey
    -0.10
    ucc
    -0.10
    ansi
    -0.10
    POSITIVE LOGITS
    alse
    0.09
     commuting
    0.08
     quite
    0.08
     locality
    0.08
    adio
    0.08
     analy
    0.08
     ZIP
    0.08
    Infinity
    0.07
    walker
    0.07
    okia
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.