© 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. 46442
    Prev
    Next
    INDEX
    Explanations

    sacrifice

    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
     Sellers
    -0.10
    ilden
    -0.10
     tighter
    -0.09
     Concat
    -0.09
     tightly
    -0.09
     tight
    -0.09
     Casa
    -0.09
    irsch
    -0.09
    kie
    -0.09
    ref
    -0.09
    POSITIVE LOGITS
     sacrifice
    0.22
     sacrifices
    0.19
     sacrificed
    0.19
     sacrific
    0.18
     sacrificing
    0.17
     Sacr
    0.16
     altar
    0.16
     offerings
    0.16
     sacr
    0.15
     appe
    0.14
    Activations Density 0.026%

    No Known Activations