© 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. 48958
    Prev
    Next
    INDEX
    Explanations

    is there any

    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
     neither
    -0.11
     either
    -0.10
    SA
    -0.09
    ansa
    -0.08
    sa
    -0.08
     almost
    -0.08
     inevitably
    -0.08
    åĬ¡
    -0.08
    atus
    -0.08
     hardly
    -0.07
    POSITIVE LOGITS
    ï¼Ł↵↵
    0.10
     anyhow
    0.10
    iT
    0.10
     Gordon
    0.10
     exist
    0.10
     Kitt
    0.10
     Really
    0.10
     really
    0.10
     Conor
    0.10
     Lilly
    0.10
    Activations Density 0.393%

    No Known Activations