© 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. 113137
    Prev
    Next
    INDEX
    Explanations

    ensure to avoid

    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
     Gor
    -0.10
    ITH
    -0.09
    oriously
    -0.09
    [Unit
    -0.09
    engl
    -0.09
    llib
    -0.09
     langu
    -0.09
     unite
    -0.09
     obsess
    -0.09
     anx
    -0.09
    POSITIVE LOGITS
     ensure
    0.24
     avoid
    0.21
    ensure
    0.20
     ensures
    0.19
    avoid
    0.17
     Ensure
    0.17
     ensuring
    0.16
     ensured
    0.16
    Ensure
    0.15
     maximize
    0.14
    Activations Density 0.243%

    No Known Activations