© 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. 115500
    Prev
    Next
    INDEX
    Explanations

    instructions and directions

    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
     Convers
    -0.12
     accidental
    -0.12
     boasting
    -0.10
     conversations
    -0.10
     unintention
    -0.10
     Corner
    -0.10
     conversation
    -0.10
     lem
    -0.10
     Conversation
    -0.10
     accidentally
    -0.09
    POSITIVE LOGITS
     instructions
    0.28
     Instructions
    0.26
    Instructions
    0.23
    instructions
    0.23
     instructed
    0.21
     instruction
    0.21
     instruct
    0.18
     directions
    0.17
    _instructions
    0.16
     clues
    0.16
    Activations Density 0.052%

    No Known Activations