© 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. 50576
    Prev
    Next
    INDEX
    Explanations

    Phillip McGowan, Mark Langfan, Richard.B.Sanders

    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
     extended
    -0.08
     Gore
    -0.08
    lico
    -0.08
     purple
    -0.08
     sadd
    -0.08
    _extended
    -0.08
     kidd
    -0.07
     ----------------------------------------------------------------------------↵
    -0.07
    WISE
    -0.07
    venir
    -0.07
    POSITIVE LOGITS
     Moff
    0.09
     Hä
    0.09
     Rogue
    0.09
     Orchard
    0.09
     favourable
    0.08
    è²
    0.08
     scrolled
    0.08
     Morg
    0.08
    âĢ¢↵↵
    0.08
    eyJ
    0.08
    Activations Density 0.177%

    No Known Activations