© 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. 48778
    Prev
    Next
    INDEX
    Explanations

    blog post titles

    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
    agra
    -0.10
     Buch
    -0.09
     ga
    -0.09
     Martha
    -0.09
    edd
    -0.09
    ÙĬØ©
    -0.09
     Forever
    -0.08
    ifestyles
    -0.08
    ervlet
    -0.08
    eson
    -0.08
    POSITIVE LOGITS
    noon
    0.10
     Cody
    0.10
    oplay
    0.09
    akov
    0.09
     CCT
    0.09
     Installed
    0.09
     ÑĤо
    0.09
     Eld
    0.09
     ashes
    0.09
     playground
    0.09
    Activations Density 0.004%

    No Known Activations