© 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. 26416
    Prev
    Next
    INDEX
    Explanations

    wondering what

    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
     sensations
    -0.14
     feelings
    -0.13
    Feels
    -0.12
     feels
    -0.12
     feeling
    -0.12
     sensation
    -0.12
     Feel
    -0.12
    feel
    -0.11
     feel
    -0.11
     Feeling
    -0.11
    POSITIVE LOGITS
     watching
    0.39
     watched
    0.38
    Watching
    0.36
     Watching
    0.36
     witnessing
    0.35
     observing
    0.33
     witnessed
    0.32
     observed
    0.31
    watch
    0.29
     witness
    0.28
    Activations Density 0.269%

    No Known Activations