© 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. 90539
    Prev
    Next
    INDEX
    Explanations

    to pursue

    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
     courage
    -0.16
     brave
    -0.16
     cautiously
    -0.16
     brav
    -0.14
     cautious
    -0.14
     courageous
    -0.13
     bravery
    -0.13
     Brave
    -0.13
     safely
    -0.13
     hes
    -0.12
    POSITIVE LOGITS
     ask
    0.13
     asking
    0.13
     Ask
    0.12
     actually
    0.11
     overt
    0.11
     direct
    0.11
     Asking
    0.10
    appro
    0.10
    ASK
    0.10
    heel
    0.10
    Activations Density 0.034%

    No Known Activations