© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27725
    Prev
    Next
    INDEX
    Explanations

    seg + common suffixes

    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
     luck
    -0.10
    ules
    -0.09
    luck
    -0.09
    ahas
    -0.08
    IVE
    -0.08
    ivet
    -0.08
    isel
    -0.08
    IRS
    -0.08
    ory
    -0.08
     Pac
    -0.08
    POSITIVE LOGITS
    kal
    0.12
     bookmark
    0.10
    ustr
    0.10
    Bookmark
    0.10
    æį®
    0.10
     Lindsay
    0.09
     duplic
    0.09
    redo
    0.09
    avec
    0.09
     guarante
    0.09
    Activations Density 0.005%

    No Known Activations