© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 6667
    Prev
    Next
    INDEX
    Explanations

    titles of artworks and media

    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
     Gratuit
    -0.11
    <small
    -0.11
    contra
    -0.11
    tesy
    -0.10
    aker
    -0.10
     Slug
    -0.10
    [source
    -0.10
    semblies
    -0.10
    <quote
    -0.10
     FOUR
    -0.09
    POSITIVE LOGITS
    ...,
    0.14
    ...↵↵
    0.12
    ...
    0.11
    ..."
    0.11
    _then
    0.10
    ...",
    0.10
    ...'
    0.10
    â̦
    0.10
     what
    0.10
    â̦↵↵
    0.10
    Activations Density 0.172%

    No Known Activations