© 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. 15962
    Prev
    Next
    INDEX
    Explanations

    æĹ¥å®ļä¹ī

    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
     runaway
    -0.11
    aine
    -0.09
    auss
    -0.09
     dich
    -0.08
    ender
    -0.07
     POS
    -0.07
     trained
    -0.07
    gor
    -0.07
    agne
    -0.07
    aux
    -0.07
    POSITIVE LOGITS
    ¹
    0.10
     Sundays
    0.10
     unfold
    0.10
    à¸Ī
    0.10
    etical
    0.09
    chu
    0.09
    olare
    0.09
     furthermore
    0.09
     cot
    0.09
    iminal
    0.09
    Activations Density 0.004%

    No Known Activations