© 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. 48262
    Prev
    Next
    INDEX
    Explanations

    custom versions, messages, or features

    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
    pur
    -0.11
    contest
    -0.10
     Kardash
    -0.10
     purse
    -0.10
    fra
    -0.10
     Kirst
    -0.10
    ÃŁen
    -0.09
     hosted
    -0.09
    arch
    -0.09
     natural
    -0.09
    POSITIVE LOGITS
    /ref
    0.11
     shout
    0.10
    /private
    0.08
    /rem
    0.08
     Col
    0.08
    raf
    0.08
     funk
    0.08
     nood
    0.08
    -col
    0.08
    Facing
    0.08
    Activations Density 0.003%

    No Known Activations