© 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. 27568
    Prev
    Next
    INDEX
    Explanations

    chapter or section numbers

    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
     Kardash
    -0.08
    ogany
    -0.08
    ipur
    -0.08
    isque
    -0.08
    udget
    -0.08
    !!)↵
    -0.08
    anter
    -0.08
    rish
    -0.08
    oeff
    -0.08
     Dw
    -0.08
    POSITIVE LOGITS
     nineteen
    0.11
     protagonist
    0.10
     Chapters
    0.10
     Chapter
    0.10
    alon
    0.09
     freshmen
    0.09
     fifteen
    0.09
    '"
    0.09
     seventeen
    0.09
     steadfast
    0.09
    Activations Density 0.059%

    No Known Activations