© 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. 48978
    Prev
    Next
    INDEX
    Explanations

    a followed by noun

    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
     vis
    -0.11
     introdu
    -0.09
     Garner
    -0.09
     repe
    -0.09
    viz
    -0.09
    empo
    -0.09
    omap
    -0.09
     indeb
    -0.09
    455
    -0.09
    jar
    -0.09
    POSITIVE LOGITS
     majority
    0.13
     shift
    0.12
     handful
    0.12
     tipping
    0.12
     subset
    0.12
     slew
    0.12
     minority
    0.11
     divide
    0.11
     trend
    0.10
    uteur
    0.10
    Activations Density 0.684%

    No Known Activations