© 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. 31094
    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
     hung
    -0.07
     stub
    -0.07
     Hung
    -0.07
     Ri
    -0.07
     Scient
    -0.07
     Hang
    -0.07
     Twins
    -0.07
     Tale
    -0.07
     E
    -0.07
     slag
    -0.07
    POSITIVE LOGITS
    uster
    0.12
     tilt
    0.11
     tac
    0.11
    loh
    0.11
    fallback
    0.11
    WG
    0.11
     paraph
    0.11
    apur
    0.10
    manda
    0.10
    alo
    0.10
    Activations Density 0.000%

    No Known Activations