© 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. 26668
    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
    rier
    -0.08
    mas
    -0.08
    vice
    -0.08
     en
    -0.07
    anic
    -0.07
    bler
    -0.07
     Abb
    -0.07
     spont
    -0.07
    mak
    -0.07
     mus
    -0.07
    POSITIVE LOGITS
    ichtig
    0.11
     Loose
    0.11
     Underground
    0.10
     Dough
    0.10
     Proud
    0.10
     Womens
    0.10
     Reb
    0.10
    inka
    0.10
     Welt
    0.10
     underground
    0.10
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.