© 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. 17494
    Prev
    Next
    INDEX
    Explanations

    speaking and saying

    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
     Antworten
    -0.10
    Showing
    -0.10
    ilon
    -0.09
    iano
    -0.09
    .blog
    -0.09
    uve
    -0.09
    Laugh
    -0.08
     handwritten
    -0.08
     üzer
    -0.08
    shots
    -0.08
    POSITIVE LOGITS
     speak
    0.22
     speaking
    0.20
     say
    0.18
     utter
    0.17
     spoke
    0.17
     speaks
    0.16
     saying
    0.16
    说
    0.16
     SPE
    0.15
     said
    0.15
    Activations Density 0.244%

    No Known Activations