© 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. 26796
    Prev
    Next
    INDEX
    Explanations

    artist installation

    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
     brag
    -0.10
     guarante
    -0.10
     Gratuit
    -0.09
     fallback
    -0.09
     tavern
    -0.09
     loyal
    -0.09
     Shaft
    -0.09
    Picture
    -0.09
     Claw
    -0.09
     briefing
    -0.09
    POSITIVE LOGITS
     installation
    0.25
     installations
    0.24
     Installation
    0.21
     artist
    0.20
    Installation
    0.20
     sculpture
    0.20
    /install
    0.19
    installation
    0.19
     sculptures
    0.19
     artworks
    0.19
    Activations Density 1.014%

    No Known Activations