© 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. 6789
    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
     scar
    -0.07
     Scar
    -0.07
     unf
    -0.07
     Bj
    -0.06
    gang
    -0.06
     Angus
    -0.06
     chased
    -0.06
    —a
    -0.06
     Hunter
    -0.06
     cref
    -0.05
    POSITIVE LOGITS
    preserve
    0.12
    istani
    0.11
    CEE
    0.11
    代
    0.11
     Mouth
    0.11
     poids
    0.11
     Wings
    0.11
    ucing
    0.10
    лем
    0.10
    izi
    0.10
    Activations Density 0.000%

    No Known Activations