© 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. 31797
    Prev
    Next
    INDEX
    Explanations

    hepatitis C

    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
     tang
    -0.12
     Tang
    -0.12
    nes
    -0.11
     sever
    -0.11
    mund
    -0.10
    ,...↵↵
    -0.10
    
    -0.10
    xing
    -0.10
     responses
    -0.10
     rocker
    -0.09
    POSITIVE LOGITS
     gentlemen
    0.08
    -archive
    0.08
     Chamber
    0.08
     Companion
    0.08
     companion
    0.08
     unlaw
    0.08
     Supporters
    0.07
     Opp
    0.07
     Geb
    0.07
     jes
    0.07
    Activations Density 0.009%

    No Known Activations