© 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. 47546
    Prev
    Next
    INDEX
    Explanations

    new, recent, novel

    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
     newer
    -0.12
     new
    -0.11
    resh
    -0.10
     devis
    -0.09
     UPDATED
    -0.09
     ing
    -0.09
     resh
    -0.09
     additional
    -0.09
     updated
    -0.08
    produk
    -0.08
    POSITIVE LOGITS
    Cli
    0.10
     através
    0.10
    533
    0.10
     tunes
    0.10
     hobbies
    0.09
     RTS
    0.09
    ctime
    0.09
     ostensibly
    0.09
    owntown
    0.09
     therefore
    0.09
    Activations Density 0.005%

    No Known Activations