© 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. 26742
    Prev
    Next
    INDEX
    Explanations

    damage done

    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
    ifi
    -0.10
     pressure
    -0.10
     Gui
    -0.10
    wat
    -0.09
     divert
    -0.09
     heav
    -0.09
     pressures
    -0.09
     Wig
    -0.09
     pleas
    -0.09
     Pressure
    -0.09
    POSITIVE LOGITS
     inflicted
    0.28
     damage
    0.27
     Damage
    0.24
    damage
    0.23
     done
    0.21
     damages
    0.20
     incurred
    0.20
    Damage
    0.20
     inflict
    0.19
     wrought
    0.19
    Activations Density 0.169%

    No Known Activations