© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 15074
    Prev
    Next
    INDEX
    Explanations

    . (followed by Tail or From)

    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
     distr
    -0.11
     Winston
    -0.10
     unlike
    -0.10
    acher
    -0.10
     Antoine
    -0.10
    antd
    -0.10
     Stall
    -0.10
    -Tr
    -0.10
    .str
    -0.10
     oss
    -0.10
    POSITIVE LOGITS
    dpi
    0.08
     wholesale
    0.08
     Barg
    0.08
    embed
    0.08
    emo
    0.08
    oyer
    0.07
    Greetings
    0.07
     pis
    0.07
    anel
    0.07
     Kle
    0.07
    Activations Density 0.003%

    No Known Activations