© 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. 89666
    Prev
    Next
    INDEX
    Explanations

    deserved killing or death

    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
    ogg
    -0.09
     unfavor
    -0.09
     Tire
    -0.09
     Gast
    -0.08
     generosity
    -0.08
     faithfully
    -0.08
    á»ı
    -0.08
     preserves
    -0.08
     Philip
    -0.08
    /apps
    -0.08
    POSITIVE LOGITS
     deserved
    0.34
     deserving
    0.23
     deserve
    0.21
     provoked
    0.21
     deserves
    0.20
     consent
    0.19
     provoke
    0.18
     consenting
    0.18
     provocative
    0.18
     prov
    0.17
    Activations Density 0.145%

    No Known Activations