© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48113
    Prev
    Next
    INDEX
    Explanations

    removal or covering

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    fers
    -0.11
    dag
    -0.11
    Modify
    -0.10
    ìĪĺ
    -0.10
     waged
    -0.10
    aira
    -0.10
    /us
    -0.10
    Scripts
    -0.10
    SetValue
    -0.10
     underlying
    -0.09
    POSITIVE LOGITS
     removal
    0.15
     removed
    0.15
    less
    0.14
     peeled
    0.14
     worn
    0.13
     Removed
    0.12
     Removal
    0.12
     covering
    0.12
    Removed
    0.11
     off
    0.11
    Activations Density 0.083%

    No Known Activations