© 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. 48858
    Prev
    Next
    INDEX
    Explanations

    carrying or holding weapons

    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
     bath
    -0.10
     Glover
    -0.10
     Lyon
    -0.09
     pill
    -0.08
    dorf
    -0.08
     masse
    -0.08
     tumble
    -0.08
     dock
    -0.08
    orie
    -0.08
     Coff
    -0.08
    POSITIVE LOGITS
     weapons
    0.42
     weapon
    0.39
     weaponry
    0.38
     guns
    0.37
     firearms
    0.36
     firearm
    0.33
     knives
    0.32
    weapons
    0.31
     rifles
    0.31
     pistols
    0.31
    Activations Density 0.592%

    No Known Activations