© 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. 30521
    Prev
    Next
    INDEX
    Explanations

    remove or eliminate

    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
     undergo
    -0.14
     abide
    -0.11
     interact
    -0.10
     remain
    -0.10
     fret
    -0.10
     behave
    -0.09
     be
    -0.09
     participate
    -0.09
     underwent
    -0.09
     engage
    -0.09
    POSITIVE LOGITS
     remove
    0.22
     eliminate
    0.20
     removes
    0.19
     removed
    0.19
     removing
    0.19
     eliminates
    0.19
     eliminating
    0.18
     eliminated
    0.17
     Elim
    0.17
    remove
    0.17
    Activations Density 1.156%

    No Known Activations