© 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. 88025
    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
     dating
    -0.14
    dating
    -0.12
     romant
    -0.11
    Dating
    -0.11
     Gallup
    -0.10
     attraction
    -0.10
     Dating
    -0.10
     romantic
    -0.10
     XYZ
    -0.10
     dates
    -0.10
    POSITIVE LOGITS
     Firm
    0.12
     again
    0.12
     Remark
    0.12
     astonished
    0.11
     astonishing
    0.11
     firm
    0.11
    again
    0.11
     extraordinarily
    0.11
     stead
    0.11
     strangely
    0.10
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.