© 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. 114678
    Prev
    Next
    INDEX
    Explanations

    hide, replace, normalize, append

    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
    nan
    -0.10
    Bron
    -0.09
    /il
    -0.09
    eger
    -0.09
    kaar
    -0.09
     arbitrary
    -0.09
    kol
    -0.08
     or
    -0.08
    Brains
    -0.08
    attr
    -0.08
    POSITIVE LOGITS
    (default
    0.13
    CurrentValue
    0.11
    .Checked
    0.11
     unchecked
    0.10
     checkbox
    0.10
     skips
    0.10
    imbus
    0.09
     Suppress
    0.09
    |min
    0.09
    /include
    0.09
    Activations Density 0.539%

    No Known Activations