© 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. 16070
    Prev
    Next
    INDEX
    Explanations

    show me how

    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
    wil
    -0.11
     Jenn
    -0.09
    itos
    -0.09
     CARE
    -0.09
    excerpt
    -0.09
    pell
    -0.08
    AMB
    -0.08
    rangle
    -0.08
     Keller
    -0.08
    XE
    -0.08
    POSITIVE LOGITS
     show
    0.13
     demonstrating
    0.12
     prove
    0.12
    >Show
    0.12
     showing
    0.12
     demonstrate
    0.12
     SHOW
    0.11
    Show
    0.11
     proving
    0.11
     Show
    0.11
    Activations Density 0.007%

    No Known Activations