© 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. 27215
    Prev
    Next
    INDEX
    Explanations

    posted on, post navigation

    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
     kne
    -0.10
    zan
    -0.09
    én
    -0.09
    arie
    -0.09
    antz
    -0.09
    nees
    -0.09
    instanc
    -0.09
     Fed
    -0.09
    ared
    -0.09
     Cosmos
    -0.08
    POSITIVE LOGITS
     Pearl
    0.09
     viv
    0.09
     powerhouse
    0.09
     Viv
    0.08
     sue
    0.08
     Wright
    0.08
     Craig
    0.08
     builders
    0.08
    soles
    0.08
     Absolute
    0.08
    Activations Density 0.012%

    No Known Activations