© 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. 91962
    Prev
    Next
    INDEX
    Explanations

    stripped bare or completely removed

    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
     nowhere
    -0.10
    eny
    -0.10
    ikon
    -0.10
    coe
    -0.09
     doorstep
    -0.09
    eria
    -0.09
    Tur
    -0.09
     Vernon
    -0.09
     Kop
    -0.09
    -re
    -0.09
    POSITIVE LOGITS
     completely
    0.11
     except
    0.10
     COMPLETE
    0.10
     stripped
    0.10
    oste
    0.10
     everything
    0.10
     complet
    0.09
     Lightweight
    0.09
     down
    0.09
    ÃŃas
    0.09
    Activations Density 0.004%

    No Known Activations