© 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. 28746
    Prev
    Next
    INDEX
    Explanations

    bombardment or bombs

    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
    upo
    -0.10
     Cunning
    -0.10
     DIM
    -0.10
    /App
    -0.09
    lator
    -0.09
    TON
    -0.09
    fon
    -0.09
    lop
    -0.09
    IBUT
    -0.09
     Ob
    -0.09
    POSITIVE LOGITS
    arded
    0.19
    shell
    0.19
    arding
    0.16
    astic
    0.14
    ardon
    0.13
     shelter
    0.13
    astically
    0.12
    Bomb
    0.11
    adier
    0.11
     shelters
    0.11
    Activations Density 0.014%

    No Known Activations