© 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. 90091
    Prev
    Next
    INDEX
    Explanations

    blame, punishing, scapegoating

    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
     brag
    -0.12
     boast
    -0.11
     Laur
    -0.11
     ger
    -0.11
     inserts
    -0.10
     tro
    -0.10
    agger
    -0.10
     complement
    -0.10
    ourke
    -0.10
     sting
    -0.10
    POSITIVE LOGITS
     blame
    0.29
     blaming
    0.25
     blames
    0.25
     blamed
    0.24
     scape
    0.22
     innocent
    0.19
     unfairly
    0.16
     punishing
    0.16
     vent
    0.16
     unrelated
    0.15
    Activations Density 0.094%

    No Known Activations