© 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. 114087
    Prev
    Next
    INDEX
    Explanations

    also known as

    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
     Watts
    -0.11
    chas
    -0.10
     typical
    -0.10
    ailable
    -0.10
     exped
    -0.10
    appro
    -0.10
    .must
    -0.10
    hoa
    -0.10
    chan
    -0.10
    emed
    -0.10
    POSITIVE LOGITS
     simply
    0.11
     spelled
    0.10
    &↵
    0.08
     interchange
    0.08
     simplement
    0.08
    lando
    0.07
    .*↵
    0.07
     Trafford
    0.07
     conj
    0.07
    >[]
    0.06
    Activations Density 0.927%

    No Known Activations