© 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. 115065
    Prev
    Next
    INDEX
    Explanations

    risk and 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
     lodge
    -0.09
     Tib
    -0.09
    apper
    -0.09
     rampage
    -0.09
     arrog
    -0.09
     Ramp
    -0.09
     enjoying
    -0.09
     apprec
    -0.09
     defaulted
    -0.09
    asking
    -0.09
    POSITIVE LOGITS
     sacrifices
    0.39
     sacrifice
    0.39
     sacrificed
    0.35
     sacrificing
    0.34
     Sacr
    0.33
     sacrific
    0.29
     risking
    0.28
     endure
    0.27
     sacr
    0.26
     inconvenience
    0.26
    Activations Density 0.264%

    No Known Activations