© 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. 49592
    Prev
    Next
    INDEX
    Explanations

    the rest of

    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
    irs
    -0.10
    nze
    -0.09
    /ag
    -0.09
     Samuel
    -0.09
     Williamson
    -0.09
    pas
    -0.09
     Sek
    -0.08
     Explos
    -0.08
     Dest
    -0.08
    issy
    -0.08
    POSITIVE LOGITS
    ocking
    0.16
    /all
    0.15
    orative
    0.14
    yled
    0.14
    ocked
    0.11
     of
    0.10
    afa
    0.10
    ock
    0.10
     assured
    0.10
    lichen
    0.10
    Activations Density 0.013%

    No Known Activations