© 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. 89302
    Prev
    Next
    INDEX
    Explanations

    hello or hi

    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
     relent
    -0.10
     promise
    -0.10
     Pes
    -0.10
    uth
    -0.10
     vis
    -0.10
     vanity
    -0.10
    promise
    -0.09
    илÑĮ
    -0.09
     promises
    -0.09
    scss
    -0.09
    POSITIVE LOGITS
     greeting
    0.27
     greeted
    0.24
     greetings
    0.24
     greet
    0.22
     hello
    0.15
    Greetings
    0.14
     gre
    0.14
     cheer
    0.13
     welcoming
    0.13
     hi
    0.13
    Activations Density 0.016%

    No Known Activations