© 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. 28228
    Prev
    Next
    INDEX
    Explanations

    click here

    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
     central
    -0.09
    
    -0.09
    ¦
    -0.09
     immortal
    -0.09
    central
    -0.09
    -date
    -0.09
    chner
    -0.09
    iod
    -0.09
    abl
    -0.09
    KEEP
    -0.09
    POSITIVE LOGITS
     Hann
    0.09
     Footer
    0.08
     again
    0.08
     Leer
    0.08
    Divider
    0.08
    AGAIN
    0.08
     !=↵
    0.08
    ëĭ
    0.08
     Divider
    0.08
    _but
    0.08
    Activations Density 0.256%

    No Known Activations