© 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. 26382
    Prev
    Next
    INDEX
    Explanations

    violence and 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
    anime
    -0.09
     anime
    -0.08
    raq
    -0.07
     clown
    -0.07
     Anime
    -0.07
    dg
    -0.07
    breaker
    -0.07
     Playstation
    -0.07
     skate
    -0.07
     foreclosure
    -0.07
    POSITIVE LOGITS
    alu
    0.13
     unmarried
    0.12
     upto
    0.12
     aun
    0.12
     nth
    0.11
    erties
    0.11
     Dub
    0.11
     tant
    0.11
     sare
    0.11
     Gow
    0.11
    Activations Density 0.020%

    No Known Activations