© 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. 4287
    Prev
    Next
    INDEX
    Explanations

    injury

    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
     outward
    -0.08
     mitt
    -0.08
     Counter
    -0.08
     Targets
    -0.07
    redirect
    -0.07
     Host
    -0.07
     impoverished
    -0.07
    UU
    -0.07
     Greenwood
    -0.07
     outreach
    -0.07
    POSITIVE LOGITS
     injury
    0.38
     Injury
    0.34
     injuries
    0.34
     injured
    0.33
     injuring
    0.25
     inj
    0.24
    juries
    0.23
     sidelined
    0.23
     sidel
    0.21
    jured
    0.20
    Activations Density 1.016%

    No Known Activations