© 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. 28307
    Prev
    Next
    INDEX
    Explanations

    clear signs or descriptions

    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
     Undo
    -0.11
     undo
    -0.11
     Peel
    -0.10
     unfolding
    -0.10
     uncover
    -0.10
     overturn
    -0.10
    713
    -0.10
     unveiling
    -0.10
     unrealistic
    -0.10
    ãģ°
    -0.10
    POSITIVE LOGITS
     therein
    0.12
     comfortably
    0.11
     slightly
    0.11
     clearly
    0.11
     evident
    0.10
     faint
    0.10
     unmistak
    0.10
     hinted
    0.09
    ena
    0.09
     occasional
    0.09
    Activations Density 0.012%

    No Known Activations