© 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. 28785
    Prev
    Next
    INDEX
    Explanations

    speaking loudly or expressing emotion

    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
     trickle
    -0.14
     slowly
    -0.14
     calmly
    -0.13
     murm
    -0.12
     peacefully
    -0.12
     cautiously
    -0.12
     omin
    -0.12
     muttered
    -0.12
     nib
    -0.11
     smirk
    -0.11
    POSITIVE LOGITS
     exclaimed
    0.34
     shout
    0.33
     shouted
    0.31
     shouting
    0.29
     shouts
    0.29
     yell
    0.27
     yelled
    0.26
     yelling
    0.25
     excl
    0.24
     cried
    0.21
    Activations Density 0.019%

    No Known Activations