© 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. 33389
    Prev
    Next
    INDEX
    Explanations

    ways to start explanations

    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
     btw
    -0.11
    /lic
    -0.10
     ".↵
    -0.10
     "?
    -0.09
    rush
    -0.09
     (↵↵
    -0.09
    =_
    -0.09
     Rouge
    -0.09
    ief
    -0.08
    caf
    -0.08
    POSITIVE LOGITS
     onwards
    0.11
     Cent
    0.11
    íĬ¼
    0.10
     onto
    0.10
     sto
    0.10
     Ont
    0.10
    ..↵↵↵↵
    0.10
     lets
    0.10
    ...↵↵↵↵
    0.10
    Ont
    0.09
    Activations Density 0.010%

    No Known Activations