© 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. 113327
    Prev
    Next
    INDEX
    Explanations

    "good", "fair", "fine" followed by affirmative or follow-up word

    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
     yup
    -0.13
     Yup
    -0.12
    954
    -0.11
     Lov
    -0.11
    aments
    -0.10
     yay
    -0.10
     Nah
    -0.10
    ments
    -0.10
    AGE
    -0.10
     âĢ¦↵↵
    -0.10
    POSITIVE LOGITS
     answer
    0.11
     answered
    0.10
     reply
    0.10
     answering
    0.09
     loyal
    0.09
     gut
    0.08
     answers
    0.08
     then
    0.08
    igg
    0.08
     girl
    0.08
    Activations Density 0.005%

    No Known Activations