© 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. 50314
    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
    elib
    -0.12
    laden
    -0.12
     tops
    -0.11
    eso
    -0.11
     dab
    -0.11
    ael
    -0.11
     vib
    -0.11
    osc
    -0.11
    ìĺ
    -0.11
     }:
    -0.11
    POSITIVE LOGITS
    ichi
    0.08
     amor
    0.08
     greed
    0.08
     preprocess
    0.07
     exploitation
    0.07
    ache
    0.07
    akan
    0.07
    âĢķ
    0.07
     Sears
    0.07
     sow
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.