© 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. 33811
    Prev
    Next
    INDEX
    Explanations

    journal titles and news headings

    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
    <|endoftext|>
    -0.12
     comple
    -0.10
    umber
    -0.09
    beros
    -0.09
    oret
    -0.09
    ,
    -0.09
    <![
    -0.08
     [...]↵↵
    -0.08
     ",
    -0.08
     âĢ¦↵↵
    -0.08
    POSITIVE LOGITS
    -header
    0.10
    :+
    0.10
     wÅĤa
    0.10
     vocab
    0.09
    âĢİ
    0.09
     IMO
    0.09
    chapter
    0.09
    News
    0.09
    ¦¬
    0.09
     suger
    0.09
    Activations Density 1.875%

    No Known Activations