© 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. 91398
    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
     sorts
    -0.13
     sund
    -0.12
     reim
    -0.12
     hut
    -0.12
     Hut
    -0.11
    luck
    -0.10
     Tales
    -0.10
     locate
    -0.10
    abic
    -0.10
    vat
    -0.10
    POSITIVE LOGITS
     gloves
    0.09
     RSVP
    0.08
    az
    0.08
    ERIC
    0.07
     pioneers
    0.07
     hier
    0.07
     youngest
    0.07
    erek
    0.07
     electric
    0.07
     Steele
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.