© 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. 14822
    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
     intercepted
    -0.10
    oks
    -0.10
     propos
    -0.10
     recom
    -0.09
    bine
    -0.09
     interception
    -0.09
     demonstr
    -0.08
    sters
    -0.08
    gle
    -0.08
    mino
    -0.08
    POSITIVE LOGITS
     McG
    0.10
     Wand
    0.09
     dpi
    0.09
    aby
    0.09
     tim
    0.09
     Ridley
    0.09
     cog
    0.09
     Lub
    0.09
    iva
    0.09
    pong
    0.09
    Activations Density 0.000%

    No Known Activations