© 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. 90192
    Prev
    Next
    INDEX
    Explanations

    at you / me / myself

    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
     draped
    -0.09
     renew
    -0.09
    hue
    -0.09
     Babe
    -0.08
     digest
    -0.08
    /mod
    -0.08
     @(
    -0.08
     fold
    -0.08
     ve
    -0.08
     Vega
    -0.08
    POSITIVE LOGITS
     him
    0.11
    Ãłng
    0.10
    /apt
    0.10
    dar
    0.10
     me
    0.10
    quence
    0.10
    elijk
    0.09
     them
    0.09
     Hilton
    0.09
    osp
    0.09
    Activations Density 0.005%

    No Known Activations