© 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. 15838
    Prev
    Next
    INDEX
    Explanations

    tissue damage or 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
     handicap
    -0.13
     nomin
    -0.12
    ebb
    -0.12
     handic
    -0.12
     Kata
    -0.12
    nore
    -0.11
    icare
    -0.11
    ihan
    -0.11
     Hancock
    -0.11
     momentos
    -0.11
    POSITIVE LOGITS
     cause
    0.13
     causing
    0.13
     aggravated
    0.12
     exacerbated
    0.12
     irritation
    0.12
     bru
    0.12
     improper
    0.11
     caused
    0.11
     causes
    0.11
     resulting
    0.11
    Activations Density 1.016%

    No Known Activations