© 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. 89053
    Prev
    Next
    INDEX
    Explanations

    well, bueno, ya, then, fact

    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
     realization
    -0.09
     simultaneously
    -0.08
     DEAL
    -0.08
     meanwhile
    -0.08
     vac
    -0.08
    ort
    -0.08
    Carthy
    -0.08
     Olive
    -0.08
     mac
    -0.08
     Dim
    -0.07
    POSITIVE LOGITS
     Benson
    0.10
     vale
    0.09
    woo
    0.09
    ixo
    0.09
    itably
    0.09
    bye
    0.09
    eses
    0.09
    eshire
    0.09
     wicked
    0.09
     roast
    0.09
    Activations Density 0.113%

    No Known Activations