© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113777
    Prev
    Next
    INDEX
    Explanations

    chameleon, mix, chooses, real

    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
     unfamiliar
    -0.10
    ibu
    -0.09
     casualty
    -0.09
     ignor
    -0.09
     paraph
    -0.09
     trophy
    -0.09
     oral
    -0.09
     Oral
    -0.09
     quoting
    -0.09
     swallowing
    -0.09
    POSITIVE LOGITS
     uploads
    0.16
     candid
    0.15
     captivating
    0.15
     consistently
    0.15
     weekly
    0.15
     posts
    0.14
     uploaded
    0.14
     curated
    0.14
     delivers
    0.13
     showcasing
    0.13
    Activations Density 0.008%

    No Known Activations