© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 112709
    Prev
    Next
    INDEX
    Explanations

    request or instruction

    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
     catering
    -0.12
     servicing
    -0.12
    hon
    -0.12
     accommodating
    -0.11
    Offer
    -0.10
     cater
    -0.10
     Cater
    -0.10
     sympathetic
    -0.10
     honors
    -0.10
    offer
    -0.10
    POSITIVE LOGITS
     instruct
    0.23
     ordering
    0.19
     requesting
    0.18
     request
    0.18
     instructions
    0.17
     requests
    0.17
     specifying
    0.17
     Request
    0.17
     Specify
    0.16
     specify
    0.16
    Activations Density 0.495%

    No Known Activations