© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27428
    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
    cube
    -0.10
    elden
    -0.09
    sed
    -0.08
     Cha
    -0.08
    ible
    -0.08
     Sachs
    -0.08
    DDL
    -0.08
     Lum
    -0.08
    =sub
    -0.08
     Wyn
    -0.07
    POSITIVE LOGITS
    KER
    0.10
    isches
    0.10
    omat
    0.10
    atr
    0.09
    undler
    0.09
     discre
    0.09
     hn
    0.09
     bz
    0.09
    orts
    0.09
    atti
    0.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.