© 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. 25742
    Prev
    Next
    INDEX
    Explanations

    chatter chirps Chip

    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
     holy
    -0.11
     sights
    -0.10
     Holy
    -0.10
    ARY
    -0.09
     lean
    -0.09
    Holy
    -0.09
    ÅĽÄĩ
    -0.09
     flat
    -0.09
    ovah
    -0.09
     Mull
    -0.09
    POSITIVE LOGITS
     chir
    0.25
     cheerful
    0.13
     chim
    0.13
     chatter
    0.11
     happily
    0.11
     Cheer
    0.11
     birds
    0.10
    rup
    0.10
     sque
    0.10
    -up
    0.10
    Activations Density 0.008%

    No Known Activations