© 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. 6276
    Prev
    Next
    INDEX
    Explanations

    assigning blame

    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
     Accepted
    -0.08
    arella
    -0.08
     bon
    -0.07
    arra
    -0.07
     McCabe
    -0.07
     Nic
    -0.07
    /cop
    -0.07
     PUR
    -0.07
     proposition
    -0.07
    ªĮ
    -0.07
    POSITIVE LOGITS
     blame
    0.70
     blamed
    0.57
     blames
    0.51
     culprit
    0.47
     fault
    0.47
     culp
    0.47
     responsible
    0.46
     blaming
    0.42
     responsibility
    0.39
     Responsible
    0.37
    Activations Density 0.354%

    No Known Activations