© 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. 25982
    Prev
    Next
    INDEX
    Explanations

    website navigation and links

    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
    olin
    -0.09
    (Note
    -0.09
    <|endoftext|>
    -0.09
    Click
    -0.08
     wives
    -0.08
    ï¼Īç¬ij
    -0.08
     purse
    -0.08
    Note
    -0.08
     ambitious
    -0.08
     Clips
    -0.08
    POSITIVE LOGITS
    (+
    0.14
    paged
    0.13
     Home
    0.13
    header
    0.12
     Uncategorized
    0.11
     home
    0.11
    info
    0.11
    HOME
    0.11
    Home
    0.10
    isu
    0.10
    Activations Density 0.127%

    No Known Activations