© 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. 90260
    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
    leh
    -0.12
    vel
    -0.12
    ubi
    -0.12
    elled
    -0.12
    avar
    -0.11
     writ
    -0.11
    ieber
    -0.11
    ajo
    -0.11
    nda
    -0.11
    /mark
    -0.11
    POSITIVE LOGITS
     prepaid
    0.09
    RIPT
    0.09
     dinero
    0.08
     payable
    0.08
     MAS
    0.08
     punct
    0.08
     Goldberg
    0.08
     upfront
    0.07
     thereof
    0.07
     cash
    0.07
    Activations Density 0.000%

    No Known Activations