© 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. 49103
    Prev
    Next
    INDEX
    Explanations

    heaven and hell

    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
    aris
    -0.11
     Pulse
    -0.11
     Schul
    -0.11
     Humb
    -0.11
     mobility
    -0.11
    ensex
    -0.11
     unheard
    -0.11
    679
    -0.11
    .DIS
    -0.10
    crest
    -0.10
    POSITIVE LOGITS
     heaven
    0.38
     Heaven
    0.35
     hell
    0.35
     Hell
    0.33
     Satan
    0.30
     heavenly
    0.29
     eternity
    0.28
    Hell
    0.28
     devil
    0.27
     Devil
    0.25
    Activations Density 0.180%

    No Known Activations